-
SAM-dPCR: Real-Time and High-throughput Absolute Quantification of Biological Samples Using Zero-Shot Segment Anything Model
Authors:
Yuanyuan Wei,
Shanhang Luo,
Changran Xu,
Yingqi Fu,
Qingyue Dong,
Yi Zhang,
Fuyang Qu,
Guangyao Cheng,
Yi-Ping Ho,
Ho-Pui Ho,
Wu Yuan
Abstract:
Digital PCR (dPCR) has revolutionized nucleic acid diagnostics by enabling absolute quantification of rare mutations and target sequences. However, current detection methodologies face challenges, as flow cytometers are costly and complex, while fluorescence imaging methods, relying on software or manual counting, are time-consuming and prone to errors. To address these limitations, we present SAM…
▽ More
Digital PCR (dPCR) has revolutionized nucleic acid diagnostics by enabling absolute quantification of rare mutations and target sequences. However, current detection methodologies face challenges, as flow cytometers are costly and complex, while fluorescence imaging methods, relying on software or manual counting, are time-consuming and prone to errors. To address these limitations, we present SAM-dPCR, a novel self-supervised learning-based pipeline that enables real-time and high-throughput absolute quantification of biological samples. Leveraging the zero-shot SAM model, SAM-dPCR efficiently analyzes diverse microreactors with over 97.7% accuracy within a rapid processing time of 3.16 seconds. By utilizing commonly available lab fluorescence microscopes, SAM-dPCR facilitates the quantification of sample concentrations. The accuracy of SAM-dPCR is validated by the strong linear relationship observed between known and inferred sample concentrations. Additionally, SAM-dPCR demonstrates versatility through comprehensive verification using various samples and reactor morphologies. This accessible, cost-effective tool transcends the limitations of traditional detection methods or fully supervised AI models, marking the first application of SAM in nucleic acid detection or molecular diagnostics. By eliminating the need for annotated training data, SAM-dPCR holds great application potential for nucleic acid quantification in resource-limited settings.
△ Less
Submitted 22 January, 2024;
originally announced March 2024.
-
Minimax Optimal Fair Classification with Bounded Demographic Disparity
Authors:
Xianli Zeng,
Guang Cheng,
Edgar Dobriban
Abstract:
Mitigating the disparate impact of statistical machine learning methods is crucial for ensuring fairness. While extensive research aims to reduce disparity, the effect of using a \emph{finite dataset} -- as opposed to the entire population -- remains unclear. This paper explores the statistical foundations of fair binary classification with two protected groups, focusing on controlling demographic…
▽ More
Mitigating the disparate impact of statistical machine learning methods is crucial for ensuring fairness. While extensive research aims to reduce disparity, the effect of using a \emph{finite dataset} -- as opposed to the entire population -- remains unclear. This paper explores the statistical foundations of fair binary classification with two protected groups, focusing on controlling demographic disparity, defined as the difference in acceptance rates between the groups. Although fairness may come at the cost of accuracy even with infinite data, we show that using a finite sample incurs additional costs due to the need to estimate group-specific acceptance thresholds. We study the minimax optimal classification error while constraining demographic disparity to a user-specified threshold. To quantify the impact of fairness constraints, we introduce a novel measure called \emph{fairness-aware excess risk} and derive a minimax lower bound on this measure that all classifiers must satisfy. Furthermore, we propose FairBayes-DDP+, a group-wise thresholding method with an offset that we show attains the minimax lower bound. Our lower bound proofs involve several innovations. Experiments support that FairBayes-DDP+ controls disparity at the user-specified level, while being faster and having a more favorable fairness-accuracy tradeoff than several baselines.
△ Less
Submitted 26 March, 2024;
originally announced March 2024.
-
Modeling Analog Dynamic Range Compressors using Deep Learning and State-space Models
Authors:
Hanzhi Yin,
Gang Cheng,
Christian J. Steinmetz,
Ruibin Yuan,
Richard M. Stern,
Roger B. Dannenberg
Abstract:
We describe a novel approach for developing realistic digital models of dynamic range compressors for digital audio production by analyzing their analog prototypes. While realistic digital dynamic compressors are potentially useful for many applications, the design process is challenging because the compressors operate nonlinearly over long time scales. Our approach is based on the structured stat…
▽ More
We describe a novel approach for developing realistic digital models of dynamic range compressors for digital audio production by analyzing their analog prototypes. While realistic digital dynamic compressors are potentially useful for many applications, the design process is challenging because the compressors operate nonlinearly over long time scales. Our approach is based on the structured state space sequence model (S4), as implementing the state-space model (SSM) has proven to be efficient at learning long-range dependencies and is promising for modeling dynamic range compressors. We present in this paper a deep learning model with S4 layers to model the Teletronix LA-2A analog dynamic range compressor. The model is causal, executes efficiently in real time, and achieves roughly the same quality as previous deep-learning models but with fewer parameters.
△ Less
Submitted 24 March, 2024;
originally announced March 2024.
-
Approximation of RKHS Functionals by Neural Networks
Authors:
Tian-Yi Zhou,
Namjoon Suh,
Guang Cheng,
Xiaoming Huo
Abstract:
Motivated by the abundance of functional data such as time series and images, there has been a growing interest in integrating such data into neural networks and learning maps from function spaces to R (i.e., functionals). In this paper, we study the approximation of functionals on reproducing kernel Hilbert spaces (RKHS's) using neural networks. We establish the universality of the approximation…
▽ More
Motivated by the abundance of functional data such as time series and images, there has been a growing interest in integrating such data into neural networks and learning maps from function spaces to R (i.e., functionals). In this paper, we study the approximation of functionals on reproducing kernel Hilbert spaces (RKHS's) using neural networks. We establish the universality of the approximation of functionals on the RKHS's. Specifically, we derive explicit error bounds for those induced by inverse multiquadric, Gaussian, and Sobolev kernels. Moreover, we apply our findings to functional regression, proving that neural networks can accurately approximate the regression maps in generalized functional linear models. Existing works on functional learning require integration-type basis function expansions with a set of pre-specified basis functions. By leveraging the interpolating orthogonal projections in RKHS's, our proposed network is much simpler in that we use point evaluations to replace basis function expansions.
△ Less
Submitted 18 March, 2024;
originally announced March 2024.
-
FairRR: Pre-Processing for Group Fairness through Randomized Response
Authors:
Xianli Zeng,
Joshua Ward,
Guang Cheng
Abstract:
The increasing usage of machine learning models in consequential decision-making processes has spurred research into the fairness of these systems. While significant work has been done to study group fairness in the in-processing and post-processing setting, there has been little that theoretically connects these results to the pre-processing domain. This paper proposes that achieving group fairne…
▽ More
The increasing usage of machine learning models in consequential decision-making processes has spurred research into the fairness of these systems. While significant work has been done to study group fairness in the in-processing and post-processing setting, there has been little that theoretically connects these results to the pre-processing domain. This paper proposes that achieving group fairness in downstream models can be formulated as finding the optimal design matrix in which to modify a response variable in a Randomized Response framework. We show that measures of group fairness can be directly controlled for with optimal model utility, proposing a pre-processing algorithm called FairRR that yields excellent downstream model utility and fairness.
△ Less
Submitted 12 March, 2024;
originally announced March 2024.
-
Gravitational back-reaction is the Holographic Dual of Magic
Authors:
ChunJun Cao,
Gong Cheng,
Alioscia Hamma,
Lorenzo Leone,
William Munizzi,
Savatore F. E. Oliviero
Abstract:
We study interplay between magic and entanglement in quantum many-body systems. We show that non-local magic which is supported by the quantum correlations is lower bounded by the flatness of entanglement spectrum and upper bounded by the amount of entanglement in the system. We then argue that a smoothed version of non-local magic bounds the hardness of classical simulations for incompressible st…
▽ More
We study interplay between magic and entanglement in quantum many-body systems. We show that non-local magic which is supported by the quantum correlations is lower bounded by the flatness of entanglement spectrum and upper bounded by the amount of entanglement in the system. We then argue that a smoothed version of non-local magic bounds the hardness of classical simulations for incompressible states. In conformal field theories, we conjecture that the non-local magic should scale linearly with entanglement entropy but sublinearly when an approximation of the state is allowed. We support the conjectures using both analytical arguments based on unitary distillation and numerical data from an Ising CFT. If the CFT has a holographic dual, then we prove that the non-local magic vanishes if and only if there is no gravitational back-reaction. Furthermore, we show that non-local magic approximately equals the rate of change of minimal surface area in response to the change of the tension of cosmic branes in the bulk.
△ Less
Submitted 11 March, 2024;
originally announced March 2024.
-
KELLMRec: Knowledge-Enhanced Large Language Models for Recommendation
Authors:
Weiqing Luo,
Chonggang Song,
Lingling Yi,
Gong Cheng
Abstract:
The utilization of semantic information is an important research problem in the field of recommender systems, which aims to complement the missing parts of mainstream ID-based approaches. With the rise of LLM, its ability to act as a knowledge base and its reasoning capability have opened up new possibilities for this research area, making LLM-based recommendation an emerging research direction. H…
▽ More
The utilization of semantic information is an important research problem in the field of recommender systems, which aims to complement the missing parts of mainstream ID-based approaches. With the rise of LLM, its ability to act as a knowledge base and its reasoning capability have opened up new possibilities for this research area, making LLM-based recommendation an emerging research direction. However, directly using LLM to process semantic information for recommendation scenarios is unreliable and sub-optimal due to several problems such as hallucination. A promising way to cope with this is to use external knowledge to aid LLM in generating truthful and usable text. Inspired by the above motivation, we propose a Knowledge-Enhanced LLMRec method. In addition to using external knowledge in prompts, the proposed method also includes a knowledge-based contrastive learning scheme for training. Experiments on public datasets and in-enterprise datasets validate the effectiveness of the proposed method.
△ Less
Submitted 11 March, 2024;
originally announced March 2024.
-
Data Nuggets: A Method for Reducing Big Data While Preserving Data Structure
Authors:
Traymon E. Beavers,
Ge Cheng,
Yajie Duan,
Javier Cabrera,
Mariusz Lubomirski,
Dhammika Amaratunga,
Jeffrey E. Teigler
Abstract:
Big data, with NxP dimension where N is extremely large, has created new challenges for data analysis, particularly in the realm of creating meaningful clusters of data. Clustering techniques, such as K-means or hierarchical clustering are popular methods for performing exploratory analysis on large datasets. Unfortunately, these methods are not always possible to apply to big data due to memory o…
▽ More
Big data, with NxP dimension where N is extremely large, has created new challenges for data analysis, particularly in the realm of creating meaningful clusters of data. Clustering techniques, such as K-means or hierarchical clustering are popular methods for performing exploratory analysis on large datasets. Unfortunately, these methods are not always possible to apply to big data due to memory or time constraints generated by calculations of order PxN(N-1). To circumvent this problem, typically, the clustering technique is applied to a random sample drawn from the dataset: however, a weakness is that the structure of the dataset, particularly at the edges, is not necessarily maintained. We propose a new solution through the concept of "data nuggets", which reduce a large dataset into a small collection of nuggets of data, each containing a center, weight, and scale parameter. The data nuggets are then input into algorithms that compute methods such as principal components analysis and clustering in a more computationally efficient manner. We show the consistency of the data nuggets-based covariance estimator and apply the methodology of data nuggets to perform exploratory analysis of a flow cytometry dataset containing over one million observations using PCA and K-means clustering for weighted observations. Supplementary materials for this article are available online.
△ Less
Submitted 5 March, 2024;
originally announced March 2024.
-
Rate-Optimal Rank Aggregation with Private Pairwise Rankings
Authors:
Shirong Xu,
Will Wei Sun,
Guang Cheng
Abstract:
In various real-world scenarios like recommender systems and political surveys, pairwise rankings are commonly collected and utilized for rank aggregation to obtain an overall ranking of items. However, preference rankings can reveal individuals' personal preferences, underscoring the need to protect them before releasing for downstream analysis. In this paper, we address the challenge of preservi…
▽ More
In various real-world scenarios like recommender systems and political surveys, pairwise rankings are commonly collected and utilized for rank aggregation to obtain an overall ranking of items. However, preference rankings can reveal individuals' personal preferences, underscoring the need to protect them before releasing for downstream analysis. In this paper, we address the challenge of preserving privacy while ensuring the utility of rank aggregation based on pairwise rankings generated from the Bradley-Terry-Luce (BTL) model. Using the randomized response mechanism to perturb raw pairwise rankings is a common privacy protection strategy used in practice, but a critical challenge arises because the privatized rankings no longer adhere to the BTL model, resulting in significant bias in downstream rank aggregation tasks. Motivated from this, we propose a debiased randomized response mechanism to protect the raw pairwise rankings, ensuring consistent estimation of true preferences and rankings in downstream rank aggregation. Theoretically, we offer insights into the relationship between overall privacy guarantees and estimation errors from private ranking data, and establish minimax rates for estimation errors. This enables the determination of optimal privacy guarantees that balance consistency in rank aggregation with robust privacy protection. We also investigate convergence rates of expected ranking errors for partial and full ranking recovery, quantifying how privacy protection influences the specification of top-$K$ item sets and complete rankings. Our findings are validated through extensive simulations and a real application.
△ Less
Submitted 26 February, 2024;
originally announced February 2024.
-
FormulaQA: A Question Answering Dataset for Formula-Based Numerical Reasoning
Authors:
Xiao Li,
Sichen Liu,
Bolin Zhu,
Yin Zhu,
Yiwei Liu,
Gong Cheng
Abstract:
The application of formulas is a fundamental ability of humans when addressing numerical reasoning problems. However, existing numerical reasoning datasets seldom explicitly indicate the formulas employed during the reasoning steps. To bridge this gap, we propose a question answering dataset for formula-based numerical reasoning called FormulaQA, from junior high school physics examinations. We fu…
▽ More
The application of formulas is a fundamental ability of humans when addressing numerical reasoning problems. However, existing numerical reasoning datasets seldom explicitly indicate the formulas employed during the reasoning steps. To bridge this gap, we propose a question answering dataset for formula-based numerical reasoning called FormulaQA, from junior high school physics examinations. We further conduct evaluations on LLMs with size ranging from 7B to over 100B parameters utilizing zero-shot and few-shot chain-of-thoughts methods and we explored the approach of using retrieval-augmented LLMs when providing an external formula database. We also fine-tune on smaller models with size not exceeding 2B. Our empirical findings underscore the significant potential for improvement in existing models when applied to our complex, formula-driven FormulaQA.
△ Less
Submitted 20 February, 2024; v1 submitted 19 February, 2024;
originally announced February 2024.
-
A Survey on Extractive Knowledge Graph Summarization: Applications, Approaches, Evaluation, and Future Directions
Authors:
Xiaxia Wang,
Gong Cheng
Abstract:
With the continuous growth of large Knowledge Graphs (KGs), extractive KG summarization becomes a trending task. Aiming at distilling a compact subgraph with condensed information, it facilitates various downstream KG-based tasks. In this survey paper, we are among the first to provide a systematic overview of its applications and define a taxonomy for existing methods from its interdisciplinary s…
▽ More
With the continuous growth of large Knowledge Graphs (KGs), extractive KG summarization becomes a trending task. Aiming at distilling a compact subgraph with condensed information, it facilitates various downstream KG-based tasks. In this survey paper, we are among the first to provide a systematic overview of its applications and define a taxonomy for existing methods from its interdisciplinary studies. Future directions are also laid out based on our extensive and comparative review.
△ Less
Submitted 19 February, 2024;
originally announced February 2024.
-
Holographic phenomenology via overlapping degrees of freedom
Authors:
Oliver Friedrich,
ChunJun Cao,
Sean M. Carroll,
Gong Cheng,
Ashmeet Singh
Abstract:
The holographic principle suggests that regions of space contain fewer physical degrees of freedom than would be implied by conventional quantum field theory. Meanwhile, in Hilbert spaces of large dimension $2^n$, it is possible to define $N \gg n$ Pauli algebras that are nearly anti-commuting (but not quite) and which can be thought of as "overlapping degrees of freedom". We propose to model the…
▽ More
The holographic principle suggests that regions of space contain fewer physical degrees of freedom than would be implied by conventional quantum field theory. Meanwhile, in Hilbert spaces of large dimension $2^n$, it is possible to define $N \gg n$ Pauli algebras that are nearly anti-commuting (but not quite) and which can be thought of as "overlapping degrees of freedom". We propose to model the phenomenology of holographic theories by allowing field-theory modes to be overlapping, and derive potential observational consequences. In particular, we build a Fermionic quantum field whose effective degrees of freedom approximately obey area scaling and satisfy a cosmic Bekenstein bound, and compare predictions of that model to cosmic neutrino observations. Our implementation of holography implies a finite lifetime of plane waves, which depends on the overall UV cutoff of the theory. To allow for neutrino flux from blazar TXS 0506+056 to be observable, our model needs to have a cutoff $k_{\mathrm{UV}} \lesssim 500\, k_{\mathrm{LHC}}\,$. This is broadly consistent with current bounds on the energy spectrum of cosmic neutrinos from IceCube, but high energy neutrinos are a potential challenge for our model of holography. We motivate our construction via quantum mereology, i.e. using the idea that EFT degrees of freedom should emerge from an abstract theory of quantum gravity by finding quasi-classical Hilbert space decompositions. We also discuss how to extend the framework to Bosons. Finally, using results from random matrix theory we derive an analytical understanding of the energy spectrum of our theory. The numerical tools used in this work are publicly available within the GPUniverse package, https://github.com/OliverFHD/GPUniverse .
△ Less
Submitted 5 March, 2024; v1 submitted 16 February, 2024;
originally announced February 2024.
-
A magnetic reconnection model for the hot explosion with both ultraviolet and Hα wing emissions
Authors:
Guanchong Cheng,
Lei Ni,
Yajie Chen,
Jun Lin
Abstract:
Ellerman bombs (EBs) with significant H$α$ wing emissions and ultraviolet bursts (UV bursts) with strong Si IV emissions are two kinds of small transient brightening events that occur in the low solar atmosphere.We numerically investigated the magnetic reconnection process between the emerging arch magnetic field and the lower atmospheric background magnetic field. We aim to find out if the hot UV…
▽ More
Ellerman bombs (EBs) with significant H$α$ wing emissions and ultraviolet bursts (UV bursts) with strong Si IV emissions are two kinds of small transient brightening events that occur in the low solar atmosphere.We numerically investigated the magnetic reconnection process between the emerging arch magnetic field and the lower atmospheric background magnetic field. We aim to find out if the hot UV emissions and much colder H$α$ wing emissions can both appear in the same reconnection process and how they are located in the reconnection region. The open-source code NIRVANA was applied to perform the 2.5D magnetohydrodynamic (MHD) simulation. We developed the related sub-codes to include the more realistic radiative cooling process for the photosphere and chromosphere and the time-dependent ionization degree of hydrogen. The initial background magnetic field is 600 G, and the emerged magnetic field in the solar atmosphere is of the same magnitude, meaning that it results in a low- $β$ magnetic reconnection environment. We also used the radiative transfer code RH1.5D to synthesize the Si IV and H$α$ spectral line profiles based on the MHD simulation results. Magnetic reconnection between emerged and background magnetic fields creates a thin, curved current sheet, which then leads to the formation of plasmoid instability and the nonuniform density distributions. The mix of hot tenuous and much cooler dense plasmas in the turbulent reconnection region can appear at about the same height, or even in the same plasmoid. The turbulent current sheet is always in a dense plasma environment with an optical depth larger than 6.5$\times$10$^{-5}$ due to the emerged magnetic field pushing high-density plasmas upward.
△ Less
Submitted 20 February, 2024; v1 submitted 11 February, 2024;
originally announced February 2024.
-
DeMarking: A Defense for Network Flow Watermarking in Real-Time
Authors:
Yali Yuan,
Jian Ge,
Guang Cheng
Abstract:
The network flow watermarking technique associates the two communicating parties by actively modifying certain characteristics of the stream generated by the sender so that it covertly carries some special marking information. Some curious users communicating with the hidden server as a Tor client may attempt de-anonymization attacks to uncover the real identity of the hidden server by using this…
▽ More
The network flow watermarking technique associates the two communicating parties by actively modifying certain characteristics of the stream generated by the sender so that it covertly carries some special marking information. Some curious users communicating with the hidden server as a Tor client may attempt de-anonymization attacks to uncover the real identity of the hidden server by using this technique. This compromises the privacy of the anonymized communication system. Therefore, we propose a defense scheme against flow watermarking. The scheme is based on deep neural networks and utilizes generative adversarial networks to convert the original Inter-Packet Delays (IPD) into new IPDs generated by the model. We also adopt the concept of adversarial attacks to ensure that the detector will produce an incorrect classification when detecting these new IPDs. This approach ensures that these IPDs are considered "clean", effectively covering the potential watermarks. This scheme is effective against time-based flow watermarking techniques.
△ Less
Submitted 6 February, 2024; v1 submitted 6 February, 2024;
originally announced February 2024.
-
Bayes-Optimal Fair Classification with Linear Disparity Constraints via Pre-, In-, and Post-processing
Authors:
Xianli Zeng,
Guang Cheng,
Edgar Dobriban
Abstract:
Machine learning algorithms may have disparate impacts on protected groups. To address this, we develop methods for Bayes-optimal fair classification, aiming to minimize classification error subject to given group fairness constraints. We introduce the notion of \emph{linear disparity measures}, which are linear functions of a probabilistic classifier; and \emph{bilinear disparity measures}, which…
▽ More
Machine learning algorithms may have disparate impacts on protected groups. To address this, we develop methods for Bayes-optimal fair classification, aiming to minimize classification error subject to given group fairness constraints. We introduce the notion of \emph{linear disparity measures}, which are linear functions of a probabilistic classifier; and \emph{bilinear disparity measures}, which are also linear in the group-wise regression functions. We show that several popular disparity measures -- the deviations from demographic parity, equality of opportunity, and predictive equality -- are bilinear.
We find the form of Bayes-optimal fair classifiers under a single linear disparity measure, by uncovering a connection with the Neyman-Pearson lemma. For bilinear disparity measures, Bayes-optimal fair classifiers become group-wise thresholding rules. Our approach can also handle multiple fairness constraints (such as equalized odds), and the common scenario when the protected attribute cannot be used at the prediction phase.
Leveraging our theoretical results, we design methods that learn fair Bayes-optimal classifiers under bilinear disparity constraints. Our methods cover three popular approaches to fairness-aware classification, via pre-processing (Fair Up- and Down-Sampling), in-processing (Fair Cost-Sensitive Classification) and post-processing (a Fair Plug-In Rule). Our methods control disparity directly while achieving near-optimal fairness-accuracy tradeoffs. We show empirically that our methods compare favorably to existing algorithms.
△ Less
Submitted 6 February, 2024; v1 submitted 5 February, 2024;
originally announced February 2024.
-
Benefits of Transformer: In-Context Learning in Linear Regression Tasks with Unstructured Data
Authors:
Yue Xing,
Xiaofeng Lin,
Namjoon Suh,
Qifan Song,
Guang Cheng
Abstract:
In practice, it is observed that transformer-based models can learn concepts in context in the inference stage. While existing literature, e.g., \citet{zhang2023trained,huang2023context}, provide theoretical explanations on this in-context learning ability, they assume the input $x_i$ and the output $y_i$ for each sample are embedded in the same token (i.e., structured data). However, in reality,…
▽ More
In practice, it is observed that transformer-based models can learn concepts in context in the inference stage. While existing literature, e.g., \citet{zhang2023trained,huang2023context}, provide theoretical explanations on this in-context learning ability, they assume the input $x_i$ and the output $y_i$ for each sample are embedded in the same token (i.e., structured data). However, in reality, they are presented in two tokens (i.e., unstructured data \cite{wibisono2023role}). In this case, this paper conducts experiments in linear regression tasks to study the benefits of the architecture of transformers and provides some corresponding theoretical intuitions to explain why the transformer can learn from unstructured data. We study the exact components in a transformer that facilitate the in-context learning. In particular, we observe that (1) a transformer with two layers of softmax (self-)attentions with look-ahead attention mask can learn from the prompt if $y_i$ is in the token next to $x_i$ for each example; (2) positional encoding can further improve the performance; and (3) multi-head attention with a high input embedding dimension has a better prediction performance than single-head attention.
△ Less
Submitted 1 February, 2024;
originally announced February 2024.
-
Better Representations via Adversarial Training in Pre-Training: A Theoretical Perspective
Authors:
Yue Xing,
Xiaofeng Lin,
Qifan Song,
Yi Xu,
Belinda Zeng,
Guang Cheng
Abstract:
Pre-training is known to generate universal representations for downstream tasks in large-scale deep learning such as large language models. Existing literature, e.g., \cite{kim2020adversarial}, empirically observe that the downstream tasks can inherit the adversarial robustness of the pre-trained model. We provide theoretical justifications for this robustness inheritance phenomenon. Our theoreti…
▽ More
Pre-training is known to generate universal representations for downstream tasks in large-scale deep learning such as large language models. Existing literature, e.g., \cite{kim2020adversarial}, empirically observe that the downstream tasks can inherit the adversarial robustness of the pre-trained model. We provide theoretical justifications for this robustness inheritance phenomenon. Our theoretical results reveal that feature purification plays an important role in connecting the adversarial robustness of the pre-trained model and the downstream tasks in two-layer neural networks. Specifically, we show that (i) with adversarial training, each hidden node tends to pick only one (or a few) feature; (ii) without adversarial training, the hidden nodes can be vulnerable to attacks. This observation is valid for both supervised pre-training and contrastive learning. With purified nodes, it turns out that clean training is enough to achieve adversarial robustness in downstream tasks.
△ Less
Submitted 26 January, 2024;
originally announced January 2024.
-
arXiv:2401.14547
[pdf]
cond-mat.str-el
cond-mat.mes-hall
cond-mat.mtrl-sci
cond-mat.other
physics.app-ph
Discovery of a Topological Charge Density Wave
Authors:
Maksim Litskevich,
Md Shafayat Hossain,
Songbo Zhang,
Zi-Jia Cheng,
Satya N. Guin,
Nitesh Kumar,
Chandra Shekhar,
Zhiwei Wang,
Yongkai Li,
Guoqing Chang,
Jia-Xin Yin,
Qi Zhang,
Guangming Cheng,
Yu-Xiao Jiang,
Tyler A. Cochran,
Nana Shumiya,
Xian P. Yang,
Daniel Multer,
Xiaoxiong Liu,
Nan Yao,
Yugui Yao,
Claudia Felser,
Titus Neupert,
M. Zahid Hasan
Abstract:
Charge density waves (CDWs) appear in numerous condensed matter platforms, ranging from high-Tc superconductors to quantum Hall systems. Despite such ubiquity, there has been a lack of direct experimental study on boundary states that can uniquely stem from the charge order. Here, using scanning tunneling microscopy, we directly visualize the bulk and boundary phenomenology of CDW in a topological…
▽ More
Charge density waves (CDWs) appear in numerous condensed matter platforms, ranging from high-Tc superconductors to quantum Hall systems. Despite such ubiquity, there has been a lack of direct experimental study on boundary states that can uniquely stem from the charge order. Here, using scanning tunneling microscopy, we directly visualize the bulk and boundary phenomenology of CDW in a topological material, Ta2Se8I. Below the transition temperature (TCDW = 260 K), tunneling spectra on an atomically resolved lattice reveal a large insulating gap in the bulk and on the surface, exceeding 500 meV, surpassing predictions from standard weakly-coupled mean-field theory. Spectroscopic imaging confirms the presence of CDW, with LDOS maxima at the conduction band corresponding to the LDOS minima at the valence band, thus revealing a π phase difference in the respective CDW order. Concomitantly, at a monolayer step edge, we detect an in-gap boundary mode with modulations along the edge that match the CDW wavevector along the edge. Intriguingly, the phase of the edge state modulation shifts by π within the charge order gap, connecting the fully gapped bulk (and surface) conduction and valence bands via a smooth energy-phase relation. This bears similarity to the topological spectral flow of edge modes, where the boundary modes bridge the gapped bulk modes in energy and momentum magnitude but in Ta2Se8I, the connectivity distinctly occurs in energy and momentum phase. Notably, our temperature-dependent measurements indicate a vanishing of the insulating gap and the in-gap edge state above TCDW, suggesting their direct relation to CDW. The theoretical analysis also indicates that the observed boundary mode is topological and linked to CDW.
△ Less
Submitted 25 January, 2024;
originally announced January 2024.
-
On the impact of robot personalization on human-robot interaction: A review
Authors:
Jinyu Yang,
Camille Vindolet,
Julio Rogelio Guadarrama Olvera,
Gordon Cheng
Abstract:
This study reviews the impact of personalization on human-robot interaction. Firstly, the various strategies used to achieve personalization are briefly described. Secondly, the effects of personalization known to date are discussed. They are presented along with the personalized parameters, personalized features, used technology, and use case they relate to. It is observed that various positive e…
▽ More
This study reviews the impact of personalization on human-robot interaction. Firstly, the various strategies used to achieve personalization are briefly described. Secondly, the effects of personalization known to date are discussed. They are presented along with the personalized parameters, personalized features, used technology, and use case they relate to. It is observed that various positive effects have been discussed in the literature while possible negative effects seem to require further investigation.
△ Less
Submitted 22 January, 2024;
originally announced January 2024.
-
A Survey on Statistical Theory of Deep Learning: Approximation, Training Dynamics, and Generative Models
Authors:
Namjoon Suh,
Guang Cheng
Abstract:
In this article, we review the literature on statistical theories of neural networks from three perspectives. In the first part, results on excess risks for neural networks are reviewed in the nonparametric framework of regression or classification. These results rely on explicit constructions of neural networks, leading to fast convergence rates of excess risks, in that tools from the approximati…
▽ More
In this article, we review the literature on statistical theories of neural networks from three perspectives. In the first part, results on excess risks for neural networks are reviewed in the nonparametric framework of regression or classification. These results rely on explicit constructions of neural networks, leading to fast convergence rates of excess risks, in that tools from the approximation theory are adopted. Through these constructions, the width and depth of the networks can be expressed in terms of sample size, data dimension, and function smoothness. Nonetheless, their underlying analysis only applies to the global minimizer in the highly non-convex landscape of deep neural networks. This motivates us to review the training dynamics of neural networks in the second part. Specifically, we review papers that attempt to answer ``how the neural network trained via gradient-based methods finds the solution that can generalize well on unseen data.'' In particular, two well-known paradigms are reviewed: the Neural Tangent Kernel (NTK) paradigm, and Mean-Field (MF) paradigm. In the last part, we review the most recent theoretical advancements in generative models including Generative Adversarial Networks (GANs), diffusion models, and in-context learning (ICL) in the Large Language Models (LLMs). The former two models are known to be the main pillars of the modern generative AI era, while ICL is a strong capability of LLMs in learning from a few examples in the context. Finally, we conclude the paper by suggesting several promising directions for deep learning theory.
△ Less
Submitted 13 January, 2024;
originally announced January 2024.
-
Legendre-Moment Transform for Linear Ensemble Control and Computation
Authors:
Xin Ning,
Gong Cheng,
Wei Zhang,
Jr-Shin Li
Abstract:
Ensemble systems, pervasive in diverse scientific and engineering domains, pose challenges to existing control methods due to their massive scale and underactuated nature. This paper presents a dynamic moment approach to addressing theoretical and computational challenges in systems-theoretic analysis and control design for linear ensemble systems. We introduce the Legendre-moments and Legendre-mo…
▽ More
Ensemble systems, pervasive in diverse scientific and engineering domains, pose challenges to existing control methods due to their massive scale and underactuated nature. This paper presents a dynamic moment approach to addressing theoretical and computational challenges in systems-theoretic analysis and control design for linear ensemble systems. We introduce the Legendre-moments and Legendre-moment transform, which maps an ensemble system defined on the $L^2$-space to a Legendre-moment system defined on the $\ell^2$-space. We show that this pair of systems is of one-to-one correspondence and shares the same controllability property. This equivalence admits the control of an ensemble system through the control of the corresponding Legendre-moment system and inspires a unified control design scheme for linear ensemble systems using structured truncated moment systems. In particular, we develop a sampling-free ensemble control design algorithm, then conduct error analysis for control design using truncated moment systems and derive error bounds with respect to the truncation orders, which are illustrated with numerical examples.
△ Less
Submitted 3 January, 2024;
originally announced January 2024.
-
Graph Elimination Networks
Authors:
Shuo Wang,
Ge Cheng,
Yun Zhang
Abstract:
Graph Neural Networks (GNNs) are widely applied across various domains, yet they perform poorly in deep layers. Existing research typically attributes this problem to node over-smoothing, where node representations become indistinguishable after multiple rounds of propagation. In this paper, we delve into the neighborhood propagation mechanism of GNNs and discover that the real root cause of GNNs'…
▽ More
Graph Neural Networks (GNNs) are widely applied across various domains, yet they perform poorly in deep layers. Existing research typically attributes this problem to node over-smoothing, where node representations become indistinguishable after multiple rounds of propagation. In this paper, we delve into the neighborhood propagation mechanism of GNNs and discover that the real root cause of GNNs' performance degradation in deep layers lies in ineffective neighborhood feature propagation. This propagation leads to an exponential growth of a node's current representation at every propagation step, making it extremely challenging to capture valuable dependencies between long-distance nodes. To address this issue, we introduce Graph Elimination Networks (GENs), which employ a specific algorithm to eliminate redundancies during neighborhood propagation. We demonstrate that GENs can enhance nodes' perception of distant neighborhoods and extend the depth of network propagation. Extensive experiments show that GENs outperform the state-of-the-art methods on various graph-level and node-level datasets.
△ Less
Submitted 2 January, 2024;
originally announced January 2024.
-
Downstream Task-Oriented Generative Model Selections on Synthetic Data Training for Fraud Detection Models
Authors:
Yinan Cheng,
Chi-Hua Wang,
Vamsi K. Potluru,
Tucker Balch,
Guang Cheng
Abstract:
Devising procedures for downstream task-oriented generative model selections is an unresolved problem of practical importance. Existing studies focused on the utility of a single family of generative models. They provided limited insights on how synthetic data practitioners select the best family generative models for synthetic training tasks given a specific combination of machine learning model…
▽ More
Devising procedures for downstream task-oriented generative model selections is an unresolved problem of practical importance. Existing studies focused on the utility of a single family of generative models. They provided limited insights on how synthetic data practitioners select the best family generative models for synthetic training tasks given a specific combination of machine learning model class and performance metric. In this paper, we approach the downstream task-oriented generative model selections problem in the case of training fraud detection models and investigate the best practice given different combinations of model interpretability and model performance constraints. Our investigation supports that, while both Neural Network(NN)-based and Bayesian Network(BN)-based generative models are both good to complete synthetic training task under loose model interpretability constrain, the BN-based generative models is better than NN-based when synthetic training fraud detection model under strict model interpretability constrain. Our results provides practical guidance for machine learning practitioner who is interested in replacing their training dataset from real to synthetic, and shed lights on more general downstream task-oriented generative model selection problems.
△ Less
Submitted 1 January, 2024;
originally announced January 2024.
-
Improve Fidelity and Utility of Synthetic Credit Card Transaction Time Series from Data-centric Perspective
Authors:
Din-Yin Hsieh,
Chi-Hua Wang,
Guang Cheng
Abstract:
Exploring generative model training for synthetic tabular data, specifically in sequential contexts such as credit card transaction data, presents significant challenges. This paper addresses these challenges, focusing on attaining both high fidelity to actual data and optimal utility for machine learning tasks. We introduce five pre-processing schemas to enhance the training of the Conditional Pr…
▽ More
Exploring generative model training for synthetic tabular data, specifically in sequential contexts such as credit card transaction data, presents significant challenges. This paper addresses these challenges, focusing on attaining both high fidelity to actual data and optimal utility for machine learning tasks. We introduce five pre-processing schemas to enhance the training of the Conditional Probabilistic Auto-Regressive Model (CPAR), demonstrating incremental improvements in the synthetic data's fidelity and utility. Upon achieving satisfactory fidelity levels, our attention shifts to training fraud detection models tailored for time-series data, evaluating the utility of the synthetic data. Our findings offer valuable insights and practical guidelines for synthetic data practitioners in the finance sector, transitioning from real to synthetic datasets for training purposes, and illuminating broader methodologies for synthesizing credit card transaction time series.
△ Less
Submitted 1 January, 2024;
originally announced January 2024.
-
XuanCe: A Comprehensive and Unified Deep Reinforcement Learning Library
Authors:
Wenzhang Liu,
Wenzhe Cai,
Kun Jiang,
Guangran Cheng,
Yuanda Wang,
Jiawei Wang,
Jingyu Cao,
Lele Xu,
Chaoxu Mu,
Changyin Sun
Abstract:
In this paper, we present XuanCe, a comprehensive and unified deep reinforcement learning (DRL) library designed to be compatible with PyTorch, TensorFlow, and MindSpore. XuanCe offers a wide range of functionalities, including over 40 classical DRL and multi-agent DRL algorithms, with the flexibility to easily incorporate new algorithms and environments. It is a versatile DRL library that support…
▽ More
In this paper, we present XuanCe, a comprehensive and unified deep reinforcement learning (DRL) library designed to be compatible with PyTorch, TensorFlow, and MindSpore. XuanCe offers a wide range of functionalities, including over 40 classical DRL and multi-agent DRL algorithms, with the flexibility to easily incorporate new algorithms and environments. It is a versatile DRL library that supports CPU, GPU, and Ascend, and can be executed on various operating systems such as Ubuntu, Windows, MacOS, and EulerOS. Extensive benchmarks conducted on popular environments including MuJoCo, Atari, and StarCraftII multi-agent challenge demonstrate the library's impressive performance. XuanCe is open-source and can be accessed at https://github.com/agi-brain/xuance.git.
△ Less
Submitted 25 December, 2023;
originally announced December 2023.
-
Discovery of a topological exciton insulator with tunable momentum order
Authors:
Md Shafayat Hossain,
Tyler A. Cochran,
Yu-Xiao Jiang,
Songbo Zhang,
Huangyu Wu,
Xiaoxiong Liu,
Xiquan Zheng,
Byunghoon Kim,
Guangming Cheng,
Qi Zhang,
Maksim Litskevich,
Junyi Zhang,
Zi-Jia Cheng,
Jinjin Liu,
Jia-Xin Yin,
Xian P. Yang,
Jonathan Denlinger,
Massimo Tallarida,
Ji Dai,
Elio Vescovo,
Anil Rajapitamahuni,
Hu Miao,
Nan Yao,
Yingying Peng,
Yugui Yao
, et al. (4 additional authors not shown)
Abstract:
Topology and correlations are fundamental concepts in modern physics, but their simultaneous occurrence within a single quantum phase is exceptionally rare. In this study, we present the discovery of such a phase of matter in Ta2Pd3Te5, a semimetal where the Coulomb interaction between electrons and holes leads to the spontaneous formation of excitonic bound states below T=100 K. Our spectroscopy…
▽ More
Topology and correlations are fundamental concepts in modern physics, but their simultaneous occurrence within a single quantum phase is exceptionally rare. In this study, we present the discovery of such a phase of matter in Ta2Pd3Te5, a semimetal where the Coulomb interaction between electrons and holes leads to the spontaneous formation of excitonic bound states below T=100 K. Our spectroscopy unveils the development of an insulating gap stemming from the condensation of these excitons, thus giving rise to a highly sought-after correlated quantum phase known as the excitonic insulator. Remarkably, our scanning tunneling microscopy measurements reveal the presence of gapless boundary modes in the excitonic insulator state. Their magnetic field response and our theoretical calculations suggest a topological origin of these modes, rendering Ta2Pd3Te5 as the first experimentally identified topological excitonic insulator in a three-dimensional material not masked by any structural phase transition. Furthermore, our study uncovers a secondary excitonic instability below T=5 K, which differs from the primary one in having finite momentum. We observe unprecedented tunability of its wavevector by an external magnetic field. These findings unlock a frontier in the study of novel correlated topological phases of matter and their tunability.
△ Less
Submitted 25 December, 2023;
originally announced December 2023.
-
Transport response of topological hinge modes in $α$-Bi$_4$Br$_4$
Authors:
Md Shafayat Hossain,
Qi Zhang,
Zhiwei Wang,
Nikhil Dhale,
Wenhao Liu,
Maksim Litskevich,
Brian Casas,
Nana Shumiya,
Jia-Xin Yin,
Tyler A. Cochran,
Yongkai Li,
Yu-Xiao Jiang,
Ying Yang,
Guangming Cheng,
Zi-Jia Cheng,
Xian P. Yang,
Nan Yao,
Titus Neupert,
Luis Balicas,
Yugui Yao,
Bing Lv,
M. Zahid Hasan
Abstract:
Electronic topological phases are renowned for their unique properties, where conducting surface states exist on the boundary of an insulating three-dimensional bulk. While the transport response of the surface states has been extensively studied, the response of the topological hinge modes remains elusive. Here, we investigate a layered topological insulator $α$-Bi$_4$Br$_4$, and provide the firs…
▽ More
Electronic topological phases are renowned for their unique properties, where conducting surface states exist on the boundary of an insulating three-dimensional bulk. While the transport response of the surface states has been extensively studied, the response of the topological hinge modes remains elusive. Here, we investigate a layered topological insulator $α$-Bi$_4$Br$_4$, and provide the first evidence for quantum transport in gapless topological hinge states existing within the insulating bulk and surface energy gaps. Our magnetoresistance measurements reveal pronounced h/e periodic (where h denotes Planck's constant and e represents the electron charge) Aharonov-Bohm oscillation. The observed periodicity, which directly reflects the enclosed area of phase-coherent electron propagation, matches the area enclosed by the sample hinges, providing compelling evidence for the quantum interference of electrons circumnavigating around the hinges. Notably, the h/e oscillations evolve as a function of magnetic field orientation, following the interference paths along the hinge modes that are allowed by topology and symmetry, and in agreement with the locations of the hinge modes according to our scanning tunneling microscopy images. Remarkably, this demonstration of quantum transport in a topological insulator can be achieved using a flake geometry and we show that it remains robust even at elevated temperatures. Our findings collectively reveal the quantum transport response of topological hinge modes with both topological nature and quantum coherence, which can be directly applied to the development of efficient quantum electronic devices.
△ Less
Submitted 14 February, 2024; v1 submitted 14 December, 2023;
originally announced December 2023.
-
MalPurifier: Enhancing Android Malware Detection with Adversarial Purification against Evasion Attacks
Authors:
Yuyang Zhou,
Guang Cheng,
Zongyao Chen,
Shui Yu
Abstract:
Machine learning (ML) has gained significant adoption in Android malware detection to address the escalating threats posed by the rapid proliferation of malware attacks. However, recent studies have revealed the inherent vulnerabilities of ML-based detection systems to evasion attacks. While efforts have been made to address this critical issue, many of the existing defensive methods encounter cha…
▽ More
Machine learning (ML) has gained significant adoption in Android malware detection to address the escalating threats posed by the rapid proliferation of malware attacks. However, recent studies have revealed the inherent vulnerabilities of ML-based detection systems to evasion attacks. While efforts have been made to address this critical issue, many of the existing defensive methods encounter challenges such as lower effectiveness or reduced generalization capabilities. In this paper, we introduce a novel Android malware detection method, MalPurifier, which exploits adversarial purification to eliminate perturbations independently, resulting in attack mitigation in a light and flexible way. Specifically, MalPurifier employs a Denoising AutoEncoder (DAE)-based purification model to preprocess input samples, removing potential perturbations from them and then leading to correct classification. To enhance defense effectiveness, we propose a diversified adversarial perturbation mechanism that strengthens the purification model against different manipulations from various evasion attacks. We also incorporate randomized "protective noises" onto benign samples to prevent excessive purification. Furthermore, we customize a loss function for improving the DAE model, combining reconstruction loss and prediction loss, to enhance feature representation learning, resulting in accurate reconstruction and classification. Experimental results on two Android malware datasets demonstrate that MalPurifier outperforms the state-of-the-art defenses, and it significantly strengthens the vulnerable malware detector against 37 evasion attacks, achieving accuracies over 90.91%. Notably, MalPurifier demonstrates easy scalability to other detectors, offering flexibility and robustness in its implementation.
△ Less
Submitted 11 December, 2023;
originally announced December 2023.
-
Modeling of SCADA and PMU Measurement Chains
Authors:
Gang Cheng,
Yuzhang Lin
Abstract:
In this document, the supervisory control and data acquisition (SCADA) and phasor measurement unit (PMU) measurement chain modeling will be studied, where the measurement error sources of each component in the SCADA and PMU measurement chains and the reasons leading to measurement errors exhibiting non-zero-mean, non-Gaussian, and time-varying statistical characteristic are summarized and analyzed…
▽ More
In this document, the supervisory control and data acquisition (SCADA) and phasor measurement unit (PMU) measurement chain modeling will be studied, where the measurement error sources of each component in the SCADA and PMU measurement chains and the reasons leading to measurement errors exhibiting non-zero-mean, non-Gaussian, and time-varying statistical characteristic are summarized and analyzed. This document provides a few equations, figures, and discussions about the details of the SCADA and PMU measurement error chain modeling, which are intended to facilitate the understanding of how the measurement errors are designed for each component in the SCADA and PMU measurement chains. The measurement chain models described here are also used for synthesizing measurement errors with realistic characteristics in simulation cases to test the developed algorithms or methodologies.
△ Less
Submitted 27 February, 2024; v1 submitted 5 December, 2023;
originally announced December 2023.
-
Survey on deep learning in multimodal medical imaging for cancer detection
Authors:
Yan Tian,
Zhaocheng Xu,
Yujun Ma,
Weiping Ding,
Ruili Wang,
Zhihong Gao,
Guohua Cheng,
Linyang He,
Xuran Zhao
Abstract:
The task of multimodal cancer detection is to determine the locations and categories of lesions by using different imaging techniques, which is one of the key research methods for cancer diagnosis. Recently, deep learning-based object detection has made significant developments due to its strength in semantic feature extraction and nonlinear function fitting. However, multimodal cancer detection r…
▽ More
The task of multimodal cancer detection is to determine the locations and categories of lesions by using different imaging techniques, which is one of the key research methods for cancer diagnosis. Recently, deep learning-based object detection has made significant developments due to its strength in semantic feature extraction and nonlinear function fitting. However, multimodal cancer detection remains challenging due to morphological differences in lesions, interpatient variability, difficulty in annotation, and imaging artifacts. In this survey, we mainly investigate over 150 papers in recent years with respect to multimodal cancer detection using deep learning, with a focus on datasets and solutions to various challenges such as data annotation, variance between classes, small-scale lesions, and occlusion. We also provide an overview of the advantages and drawbacks of each approach. Finally, we discuss the current scope of work and provide directions for the future development of multimodal cancer detection.
△ Less
Submitted 3 December, 2023;
originally announced December 2023.
-
Deep Learning Assisted Raman Spectroscopy for Rapid Identification of 2D Materials
Authors:
Yaping Qi,
Dan Hu,
Zhenping Wu,
Ming Zheng,
Guanghui Cheng,
Yucheng Jiang,
Yong P. Chen
Abstract:
Two-dimensional (2D) materials have attracted extensive attention due to their unique characteristics and application potentials. Raman spectroscopy, as a rapid and non-destructive probe, exhibits distinct features and holds notable advantages in the structural characterization of 2D materials. However, traditional data analysis of Raman spectra relies on manual interpretation and feature extracti…
▽ More
Two-dimensional (2D) materials have attracted extensive attention due to their unique characteristics and application potentials. Raman spectroscopy, as a rapid and non-destructive probe, exhibits distinct features and holds notable advantages in the structural characterization of 2D materials. However, traditional data analysis of Raman spectra relies on manual interpretation and feature extraction, which are both time-consuming and subjective. In this work, we employ deep learning techniques, including classificatory and generative deep learning, to assist the analysis of Raman spectra of typical 2D materials. For the limited and unevenly distributed Raman spectral data, we propose a data augmentation approach based on Denoising Diffusion Probabilistic Models (DDPM) to augment the training dataset and construct a four-layer Convolutional Neural Network (CNN) for 2D material classification. Experimental results illustrate the effectiveness of DDPM in addressing data limitations and significantly improved classification model performance. The proposed DDPM-CNN method shows high reliability, with 100%classification accuracy. Our work demonstrates the practicality of deep learning-assisted Raman spectroscopy for high-precision recognition and classification of 2D materials, offering a promising avenue for rapid and automated spectral analysis.
△ Less
Submitted 3 December, 2023;
originally announced December 2023.
-
DGMem: Learning Visual Navigation Policy without Any Labels by Dynamic Graph Memory
Authors:
Wenzhe Cai,
Teng Wang,
Guangran Cheng,
Lele Xu,
Changyin Sun
Abstract:
In recent years, learning-based approaches have demonstrated significant promise in addressing intricate navigation tasks. Traditional methods for training deep neural network navigation policies rely on meticulously designed reward functions or extensive teleoperation datasets as navigation demonstrations. However, the former is often confined to simulated environments, and the latter demands sub…
▽ More
In recent years, learning-based approaches have demonstrated significant promise in addressing intricate navigation tasks. Traditional methods for training deep neural network navigation policies rely on meticulously designed reward functions or extensive teleoperation datasets as navigation demonstrations. However, the former is often confined to simulated environments, and the latter demands substantial human labor, making it a time-consuming process. Our vision is for robots to autonomously learn navigation skills and adapt their behaviors to environmental changes without any human intervention. In this work, we discuss the self-supervised navigation problem and present Dynamic Graph Memory (DGMem), which facilitates training only with on-board observations. With the help of DGMem, agents can actively explore their surroundings, autonomously acquiring a comprehensive navigation policy in a data-efficient manner without external feedback. Our method is evaluated in photorealistic 3D indoor scenes, and empirical studies demonstrate the effectiveness of DGMem.
△ Less
Submitted 30 November, 2023;
originally announced November 2023.
-
Exact fixed-point tensor network construction for rational conformal field theory
Authors:
Gong Cheng,
Lin Chen,
Zheng-Cheng Gu,
Ling-Yan Hung
Abstract:
The novel concept of entanglement renormalization and its corresponding tensor network renormalization technique have been highly successful in developing a controlled real space renormalization group (RG) scheme for classical 2D systems or $(1+1)$D quantum systems. Numerically approximate fixed-point (FP) tensors are widely used to extract the conformal data of the underlying conformal field theo…
▽ More
The novel concept of entanglement renormalization and its corresponding tensor network renormalization technique have been highly successful in developing a controlled real space renormalization group (RG) scheme for classical 2D systems or $(1+1)$D quantum systems. Numerically approximate fixed-point (FP) tensors are widely used to extract the conformal data of the underlying conformal field theory (CFT) describing critical phenomena. In this paper, we present an explicit analytical construction of the FP tensor for 2D rational CFT (RCFT). We define it as a correlation function between the "boundary-changing operators" on triangles. Our construction fully captures all the real-space RG conditions. We also provide a concrete example using the Ising model to compute the scaling dimensions explicitly based on the corresponding FP tensor. Interestingly, our construction of FP tensors is closely related to a strange correlator, where the holographic picture naturally emerges.
△ Less
Submitted 20 February, 2024; v1 submitted 29 November, 2023;
originally announced November 2023.
-
Strain mediated phase crossover in Ruddlesden Popper nickelates
Authors:
Ting Cui,
Songhee Choi,
Ting Lin,
Chen Liu,
Gang Wang,
Ningning Wang,
Shengru Chen,
Haitao Hong,
Dongke Rong,
Qianying Wang,
Qiao Jin,
Jia-Ou Wang,
Lin Gu,
Chen Ge,
Can Wang,
Jin Guang Cheng,
Qinghua Zhang,
Liang Si,
Kui-juan Jin,
Er-Jia Guo
Abstract:
Recent progress on the signatures of pressure-induced high temperature superconductivity in Ruddlesden Popper (RP) nickelates (Lan+1NinO3n+1) has attracted growing interest in both theoretical calculations and experimental efforts. The fabrication of high-quality single crystalline RP nickelate thin films is critical for possible reducing the superconducting transition pressure and advancing appli…
▽ More
Recent progress on the signatures of pressure-induced high temperature superconductivity in Ruddlesden Popper (RP) nickelates (Lan+1NinO3n+1) has attracted growing interest in both theoretical calculations and experimental efforts. The fabrication of high-quality single crystalline RP nickelate thin films is critical for possible reducing the superconducting transition pressure and advancing applications in microelectronics in the future. In this study, we report the observations of an active phase transition in RP nickelate films induced by misfit strain. We found that RP nickelate films favor the perovskite structure (n = infinite) under tensile strains, while compressive strains stabilize the La3Ni2O7 (n = 2) phase. The selection of distinct phases is governed by the strain dependent formation energy and electronic configuration. In compressively strained La3Ni2O7, we experimentally determined splitting energy is ~0.2 eV and electrons prefer to occupy in-plane orbitals. First principles calculations unveil a robust coupling between strain effects and the valence state of Ni ions in RP nickelates, suggesting a dual driving force for the inevitable phase co-existence transition in RP nickelates. Our work underscores the sensitivity of RP nickelate formation to epitaxial strain, presenting a significant challenge in fabricating pure-phase RP nickelate films. Therefore, special attention to stacking defects and grain boundaries between different RP phases is essential when discussing the pressure-induced superconductivity in RP nickelates.
△ Less
Submitted 22 November, 2023;
originally announced November 2023.
-
A Two-Stage Generative Model with CycleGAN and Joint Diffusion for MRI-based Brain Tumor Detection
Authors:
Wenxin Wang,
Zhuo-Xu Cui,
Guanxun Cheng,
Chentao Cao,
Xi Xu,
Ziwei Liu,
Haifeng Wang,
Yulong Qi,
Dong Liang,
Yanjie Zhu
Abstract:
Accurate detection and segmentation of brain tumors is critical for medical diagnosis. However, current supervised learning methods require extensively annotated images and the state-of-the-art generative models used in unsupervised methods often have limitations in covering the whole data distribution. In this paper, we propose a novel framework Two-Stage Generative Model (TSGM) that combines Cyc…
▽ More
Accurate detection and segmentation of brain tumors is critical for medical diagnosis. However, current supervised learning methods require extensively annotated images and the state-of-the-art generative models used in unsupervised methods often have limitations in covering the whole data distribution. In this paper, we propose a novel framework Two-Stage Generative Model (TSGM) that combines Cycle Generative Adversarial Network (CycleGAN) and Variance Exploding stochastic differential equation using joint probability (VE-JP) to improve brain tumor detection and segmentation. The CycleGAN is trained on unpaired data to generate abnormal images from healthy images as data prior. Then VE-JP is implemented to reconstruct healthy images using synthetic paired abnormal images as a guide, which alters only pathological regions but not regions of healthy. Notably, our method directly learned the joint probability distribution for conditional generation. The residual between input and reconstructed images suggests the abnormalities and a thresholding method is subsequently applied to obtain segmentation results. Furthermore, the multimodal results are weighted with different weights to improve the segmentation accuracy further. We validated our method on three datasets, and compared with other unsupervised methods for anomaly detection and segmentation. The DSC score of 0.8590 in BraTs2020 dataset, 0.6226 in ITCS dataset and 0.7403 in In-house dataset show that our method achieves better segmentation performance and has better generalization.
△ Less
Submitted 6 November, 2023;
originally announced November 2023.
-
Auto-ICell: An Accessible and Cost-Effective Integrative Droplet Microfluidic System for Real-Time Single-Cell Morphological and Apoptotic Analysis
Authors:
Yuanyuan Wei,
Meiai Lin,
Shanhang Luo,
Syed Muhammad Tariq Abbasi,
Liwei Tan,
Guangyao Cheng,
Bijie Bai,
Yi-Ping Ho,
Scott Wu Yuan,
Ho-Pui Ho
Abstract:
The Auto-ICell system, a novel, and cost-effective integrated droplet microfluidic system, is introduced for real-time analysis of single-cell morphology and apoptosis. This system integrates a 3D-printed microfluidic chip with image analysis algorithms, enabling the generation of uniform droplet reactors and immediate image analysis. The system employs a color-based image analysis algorithm in th…
▽ More
The Auto-ICell system, a novel, and cost-effective integrated droplet microfluidic system, is introduced for real-time analysis of single-cell morphology and apoptosis. This system integrates a 3D-printed microfluidic chip with image analysis algorithms, enabling the generation of uniform droplet reactors and immediate image analysis. The system employs a color-based image analysis algorithm in the bright field for droplet content analysis. Meanwhile, in the fluorescence field, cell apoptosis is quantitatively measured through a combination of deep-learning-enabled multiple fluorescent channel analysis and a live/dead cell stain kit. Breast cancer cells are encapsulated within uniform droplets, with diameters ranging from 70 μm to 240 μm, generated at a high throughput of 1,500 droplets per minute. Real-time image analysis results are displayed within 2 seconds on a custom graphical user interface (GUI). The system provides an automatic calculation of the distribution and ratio of encapsulated dyes in the bright field, and in the fluorescent field, cell blebbing and cell circularity are observed and quantified respectively. The Auto-ICell system is non-invasive and provides online detection, offering a robust, time-efficient, user-friendly, and cost-effective solution for single-cell analysis. It significantly enhances the detection throughput of droplet single-cell analysis by reducing setup costs and improving operational performance. This study highlights the potential of the Auto-ICell system in advancing biological research and personalized disease treatment, with promising applications in cell culture, biochemical microreactors, drug carriers, cell-based assays, synthetic biology, and point-of-care diagnostics.
△ Less
Submitted 6 November, 2023;
originally announced November 2023.
-
Constraints on ultra-slow-roll inflation with the NANOGrav 15-Year Dataset
Authors:
Bo Mu,
Jing Liu,
Gong Cheng,
Zong-Kuan Guo
Abstract:
Ultra-slow-roll~(USR) inflation predicts an exponential amplification of scalar perturbations at small scales, which leads to a stochastic gravitational wave background~(SGWB) through the coupling of the scalar and tensor modes at the second-order expansion of the Einstein equation. In this work, we search for such a scalar-induced SGWB from the NANOGrav 15-year (NG15) dataset, and find that the S…
▽ More
Ultra-slow-roll~(USR) inflation predicts an exponential amplification of scalar perturbations at small scales, which leads to a stochastic gravitational wave background~(SGWB) through the coupling of the scalar and tensor modes at the second-order expansion of the Einstein equation. In this work, we search for such a scalar-induced SGWB from the NANOGrav 15-year (NG15) dataset, and find that the SGWB from USR inflation could explain the observed data. We place constraints on the amplitude of the scalar power spectrum to $P_{\mathrm{Rp}} > 10^{-1.80}$ at $95\%$ confidence level (C.L.) at the scale of $k\sim 20\, \mathrm{pc}^{-1}$. We find that $\log_{10} P_{\mathrm{Rp}}$ degenerates with the peak scale $\log_{10} k_{\mathrm{p}}$. We also obtain the parameter space allowed by the data in the USR inflationary scenario, where the $e$-folding numbers of the duration of the USR phase has a lower limit $ΔN > 2.80$ ($95\%$ C.L.) when the USR phase ends at $N\approx 20$. Since the priors for the model parameters %in the USR model are uncertain, we do not calculate the Bayes factors. Instead, to quantify the goodness of fit, we calculate the maximum values of the log-likelihood for USR inflation, bubble collision of the cosmological phase transition, and inspiraling supermassive black hole binaries (SMBHBs), respectively. Our results imply that the SGWB from USR inflation can fit the data better than the one from SMBHBs.
△ Less
Submitted 31 October, 2023;
originally announced October 2023.
-
AutoDiff: combining Auto-encoder and Diffusion model for tabular data synthesizing
Authors:
Namjoon Suh,
Xiaofeng Lin,
Din-Yin Hsieh,
Merhdad Honarkhah,
Guang Cheng
Abstract:
Diffusion model has become a main paradigm for synthetic data generation in many subfields of modern machine learning, including computer vision, language model, or speech synthesis. In this paper, we leverage the power of diffusion model for generating synthetic tabular data. The heterogeneous features in tabular data have been main obstacles in tabular data synthesis, and we tackle this problem…
▽ More
Diffusion model has become a main paradigm for synthetic data generation in many subfields of modern machine learning, including computer vision, language model, or speech synthesis. In this paper, we leverage the power of diffusion model for generating synthetic tabular data. The heterogeneous features in tabular data have been main obstacles in tabular data synthesis, and we tackle this problem by employing the auto-encoder architecture. When compared with the state-of-the-art tabular synthesizers, the resulting synthetic tables from our model show nice statistical fidelities to the real data, and perform well in downstream tasks for machine learning utilities. We conducted the experiments over $15$ publicly available datasets. Notably, our model adeptly captures the correlations among features, which has been a long-standing challenge in tabular data synthesis. Our code is available at https://github.com/UCLA-Trustworthy-AI-Lab/AutoDiffusion.
△ Less
Submitted 16 November, 2023; v1 submitted 23 October, 2023;
originally announced October 2023.
-
OV-VG: A Benchmark for Open-Vocabulary Visual Grounding
Authors:
Chunlei Wang,
Wenquan Feng,
Xiangtai Li,
Guangliang Cheng,
Shuchang Lyu,
Binghao Liu,
Lijiang Chen,
Qi Zhao
Abstract:
Open-vocabulary learning has emerged as a cutting-edge research area, particularly in light of the widespread adoption of vision-based foundational models. Its primary objective is to comprehend novel concepts that are not encompassed within a predefined vocabulary. One key facet of this endeavor is Visual Grounding, which entails locating a specific region within an image based on a corresponding…
▽ More
Open-vocabulary learning has emerged as a cutting-edge research area, particularly in light of the widespread adoption of vision-based foundational models. Its primary objective is to comprehend novel concepts that are not encompassed within a predefined vocabulary. One key facet of this endeavor is Visual Grounding, which entails locating a specific region within an image based on a corresponding language description. While current foundational models excel at various visual language tasks, there's a noticeable absence of models specifically tailored for open-vocabulary visual grounding. This research endeavor introduces novel and challenging OV tasks, namely Open-Vocabulary Visual Grounding and Open-Vocabulary Phrase Localization. The overarching aim is to establish connections between language descriptions and the localization of novel objects. To facilitate this, we have curated a comprehensive annotated benchmark, encompassing 7,272 OV-VG images and 1,000 OV-PL images. In our pursuit of addressing these challenges, we delved into various baseline methodologies rooted in existing open-vocabulary object detection, VG, and phrase localization frameworks. Surprisingly, we discovered that state-of-the-art methods often falter in diverse scenarios. Consequently, we developed a novel framework that integrates two critical components: Text-Image Query Selection and Language-Guided Feature Attention. These modules are designed to bolster the recognition of novel categories and enhance the alignment between visual and linguistic information. Extensive experiments demonstrate the efficacy of our proposed framework, which consistently attains SOTA performance across the OV-VG task. Additionally, ablation studies provide further evidence of the effectiveness of our innovative models. Codes and datasets will be made publicly available at https://github.com/cv516Buaa/OV-VG.
△ Less
Submitted 22 October, 2023;
originally announced October 2023.
-
TransY-Net:Learning Fully Transformer Networks for Change Detection of Remote Sensing Images
Authors:
Tianyu Yan,
Zifu Wan,
Pingping Zhang,
Gong Cheng,
Huchuan Lu
Abstract:
In the remote sensing field, Change Detection (CD) aims to identify and localize the changed regions from dual-phase images over the same places. Recently, it has achieved great progress with the advances of deep learning. However, current methods generally deliver incomplete CD regions and irregular CD boundaries due to the limited representation ability of the extracted visual features. To relie…
▽ More
In the remote sensing field, Change Detection (CD) aims to identify and localize the changed regions from dual-phase images over the same places. Recently, it has achieved great progress with the advances of deep learning. However, current methods generally deliver incomplete CD regions and irregular CD boundaries due to the limited representation ability of the extracted visual features. To relieve these issues, in this work we propose a novel Transformer-based learning framework named TransY-Net for remote sensing image CD, which improves the feature extraction from a global view and combines multi-level visual features in a pyramid manner. More specifically, the proposed framework first utilizes the advantages of Transformers in long-range dependency modeling. It can help to learn more discriminative global-level features and obtain complete CD regions. Then, we introduce a novel pyramid structure to aggregate multi-level visual features from Transformers for feature enhancement. The pyramid structure grafted with a Progressive Attention Module (PAM) can improve the feature representation ability with additional inter-dependencies through spatial and channel attentions. Finally, to better train the whole framework, we utilize the deeply-supervised learning with multiple boundary-aware loss functions. Extensive experiments demonstrate that our proposed method achieves a new state-of-the-art performance on four optical and two SAR image CD benchmarks. The source code is released at https://github.com/Drchip61/TransYNet.
△ Less
Submitted 22 October, 2023;
originally announced October 2023.
-
DST-Det: Simple Dynamic Self-Training for Open-Vocabulary Object Detection
Authors:
Shilin Xu,
Xiangtai Li,
Size Wu,
Wenwei Zhang,
Yining Li,
Guangliang Cheng,
Yunhai Tong,
Kai Chen,
Chen Change Loy
Abstract:
Open-vocabulary object detection (OVOD) aims to detect the objects beyond the set of classes observed during training. This work presents a simple yet effective strategy that leverages the zero-shot classification ability of pre-trained vision-language models (VLM), such as CLIP, to directly discover proposals of possible novel classes. Unlike previous works that ignore novel classes during traini…
▽ More
Open-vocabulary object detection (OVOD) aims to detect the objects beyond the set of classes observed during training. This work presents a simple yet effective strategy that leverages the zero-shot classification ability of pre-trained vision-language models (VLM), such as CLIP, to directly discover proposals of possible novel classes. Unlike previous works that ignore novel classes during training and rely solely on the region proposal network (RPN) for novel object detection, our method selectively filters proposals based on specific design criteria. The resulting sets of identified proposals serve as pseudo-labels of potential novel classes during the training phase. This self-training strategy improves the recall and accuracy of novel classes without requiring additional annotations or datasets. We further propose a simple offline pseudo-label generation strategy to refine the object detector. Empirical evaluations on three datasets, including LVIS, V3Det, and COCO, demonstrate significant improvements over the baseline performance without incurring additional parameters or computational costs during inference. In particular, compared with previous F-VLM, our method achieves a 1.7\% improvement on the LVIS dataset. We also achieve over 6.5\% improvement on the recent challenging V3Det dataset. When combined with the recent method CLIPSelf, our method also achieves 46.7 novel class AP on COCO without introducing extra data for pertaining.
△ Less
Submitted 23 December, 2023; v1 submitted 2 October, 2023;
originally announced October 2023.
-
Robust Navigation with Cross-Modal Fusion and Knowledge Transfer
Authors:
Wenzhe Cai,
Guangran Cheng,
Lingyue Kong,
Lu Dong,
Changyin Sun
Abstract:
Recently, learning-based approaches show promising results in navigation tasks. However, the poor generalization capability and the simulation-reality gap prevent a wide range of applications. We consider the problem of improving the generalization of mobile robots and achieving sim-to-real transfer for navigation skills. To that end, we propose a cross-modal fusion method and a knowledge transfer…
▽ More
Recently, learning-based approaches show promising results in navigation tasks. However, the poor generalization capability and the simulation-reality gap prevent a wide range of applications. We consider the problem of improving the generalization of mobile robots and achieving sim-to-real transfer for navigation skills. To that end, we propose a cross-modal fusion method and a knowledge transfer framework for better generalization. This is realized by a teacher-student distillation architecture. The teacher learns a discriminative representation and the near-perfect policy in an ideal environment. By imitating the behavior and representation of the teacher, the student is able to align the features from noisy multi-modal input and reduce the influence of variations on navigation policy. We evaluate our method in simulated and real-world environments. Experiments show that our method outperforms the baselines by a large margin and achieves robust navigation performance with varying working conditions.
△ Less
Submitted 23 September, 2023;
originally announced September 2023.
-
Furthest Reasoning with Plan Assessment: Stable Reasoning Path with Retrieval-Augmented Large Language Models
Authors:
Yin Zhu,
Zhiling Luo,
Gong Cheng
Abstract:
Large Language Models (LLMs), acting as a powerful reasoner and generator, exhibit extraordinary performance across various natural language tasks, such as question answering (QA). Among these tasks, Multi-Hop Question Answering (MHQA) stands as a widely discussed category, necessitating seamless integration between LLMs and the retrieval of external knowledge. Existing methods employ LLM to gener…
▽ More
Large Language Models (LLMs), acting as a powerful reasoner and generator, exhibit extraordinary performance across various natural language tasks, such as question answering (QA). Among these tasks, Multi-Hop Question Answering (MHQA) stands as a widely discussed category, necessitating seamless integration between LLMs and the retrieval of external knowledge. Existing methods employ LLM to generate reasoning paths and plans, and utilize IR to iteratively retrieve related knowledge, but these approaches have inherent flaws. On one hand, Information Retriever (IR) is hindered by the low quality of generated queries by LLM. On the other hand, LLM is easily misguided by the irrelevant knowledge by IR. These inaccuracies, accumulated by the iterative interaction between IR and LLM, lead to a disaster in effectiveness at the end. To overcome above barriers, in this paper, we propose a novel pipeline for MHQA called Furthest-Reasoning-with-Plan-Assessment (FuRePA), including an improved framework (Furthest Reasoning) and an attached module (Plan Assessor). 1) Furthest reasoning operates by masking previous reasoning path and generated queries for LLM, encouraging LLM generating chain of thought from scratch in each iteration. This approach enables LLM to break the shackle built by previous misleading thoughts and queries (if any). 2) The Plan Assessor is a trained evaluator that selects an appropriate plan from a group of candidate plans proposed by LLM. Our methods are evaluated on three highly recognized public multi-hop question answering datasets and outperform state-of-the-art on most metrics (achieving a 10%-12% in answer accuracy).
△ Less
Submitted 22 September, 2023;
originally announced September 2023.
-
Bridging Zero-shot Object Navigation and Foundation Models through Pixel-Guided Navigation Skill
Authors:
Wenzhe Cai,
Siyuan Huang,
Guangran Cheng,
Yuxing Long,
Peng Gao,
Changyin Sun,
Hao Dong
Abstract:
Zero-shot object navigation is a challenging task for home-assistance robots. This task emphasizes visual grounding, commonsense inference and locomotion abilities, where the first two are inherent in foundation models. But for the locomotion part, most works still depend on map-based planning approaches. The gap between RGB space and map space makes it difficult to directly transfer the knowledge…
▽ More
Zero-shot object navigation is a challenging task for home-assistance robots. This task emphasizes visual grounding, commonsense inference and locomotion abilities, where the first two are inherent in foundation models. But for the locomotion part, most works still depend on map-based planning approaches. The gap between RGB space and map space makes it difficult to directly transfer the knowledge from foundation models to navigation tasks. In this work, we propose a Pixel-guided Navigation skill (PixNav), which bridges the gap between the foundation models and the embodied navigation task. It is straightforward for recent foundation models to indicate an object by pixels, and with pixels as the goal specification, our method becomes a versatile navigation policy towards all different kinds of objects. Besides, our PixNav is a pure RGB-based policy that can reduce the cost of home-assistance robots. Experiments demonstrate the robustness of the PixNav which achieves 80+% success rate in the local path-planning task. To perform long-horizon object navigation, we design an LLM-based planner to utilize the commonsense knowledge between objects and rooms to select the best waypoint. Evaluations across both photorealistic indoor simulators and real-world environments validate the effectiveness of our proposed navigation strategy. Code and video demos are available at https://github.com/wzcai99/Pixel-Navigator.
△ Less
Submitted 20 September, 2023; v1 submitted 19 September, 2023;
originally announced September 2023.
-
Improve Deep Forest with Learnable Layerwise Augmentation Policy Schedule
Authors:
Hongyu Zhu,
Sichu Liang,
Wentao Hu,
Fang-Qi Li,
Yali yuan,
Shi-Lin Wang,
Guang Cheng
Abstract:
As a modern ensemble technique, Deep Forest (DF) employs a cascading structure to construct deep models, providing stronger representational power compared to traditional decision forests. However, its greedy multi-layer learning procedure is prone to overfitting, limiting model effectiveness and generalizability. This paper presents an optimized Deep Forest, featuring learnable, layerwise data au…
▽ More
As a modern ensemble technique, Deep Forest (DF) employs a cascading structure to construct deep models, providing stronger representational power compared to traditional decision forests. However, its greedy multi-layer learning procedure is prone to overfitting, limiting model effectiveness and generalizability. This paper presents an optimized Deep Forest, featuring learnable, layerwise data augmentation policy schedules. Specifically, We introduce the Cut Mix for Tabular data (CMT) augmentation technique to mitigate overfitting and develop a population-based search algorithm to tailor augmentation intensity for each layer. Additionally, we propose to incorporate outputs from intermediate layers into a checkpoint ensemble for more stable performance. Experimental results show that our method sets new state-of-the-art (SOTA) benchmarks in various tabular classification tasks, outperforming shallow tree ensembles, deep forests, deep neural network, and AutoML competitors. The learned policies also transfer effectively to Deep Forest variants, underscoring its potential for enhancing non-differentiable deep learning modules in tabular signal processing.
△ Less
Submitted 16 September, 2023;
originally announced September 2023.
-
Can the Parker Solar Probe Detect a CME-flare Current Sheet?
Authors:
Yuhao Chen,
Zhong Liu,
Pengfei Chen,
David F. Webb,
Qi Hao,
Jialiang Hu,
Guanchong Cheng,
Zhixing Mei,
Jing Ye,
Qian Wang,
Jun Lin
Abstract:
A current sheet (CS) is the central structure in the disrupting magnetic configuration during solar eruptions. More than 90\% of the free magnetic energy (the difference between the energy in the non-potential magnetic field and that in the potential one) stored in the coronal magnetic field beforehand is converted into heating and kinetic energy of the plasma, as well as accelerating charged part…
▽ More
A current sheet (CS) is the central structure in the disrupting magnetic configuration during solar eruptions. More than 90\% of the free magnetic energy (the difference between the energy in the non-potential magnetic field and that in the potential one) stored in the coronal magnetic field beforehand is converted into heating and kinetic energy of the plasma, as well as accelerating charged particles, by magnetic reconnection occurring in the CS. However, the detailed physical properties and fine structures of the CS are still unknown since there is no relevant information obtained via in situ detections. The Parker Solar Probe (PSP) may provide us such information should it traverse a CS in the eruption. The perihelion of PSP's final orbit is located at about 10 solar radii from the center of the Sun, so it can observe the CS at a very close distance, or even traverses the CS, which provides us a unique opportunity to look into fine properties and structures of the CS, helping reveal the detailed physics of large-scale reconnection that was impossible before. We evaluate the probability that PSP can traverse a CS, and examine the orbit of a PSP-like spacecraft that has the highest probability to traverse a CS.
△ Less
Submitted 12 September, 2023;
originally announced September 2023.
-
Deep Learning Approach for Large-Scale, Real-Time Quantification of Green Fluorescent Protein-Labeled Biological Samples in Microreactors
Authors:
Yuanyuan Wei,
Sai Mu Dalike Abaxi,
Nawaz Mehmood,
Luoquan Li,
Fuyang Qu,
Guangyao Cheng,
Dehua Hu,
Yi-Ping Ho,
Scott Wu Yuan,
Ho-Pui Ho
Abstract:
Absolute quantification of biological samples entails determining expression levels in precise numerical copies, offering enhanced accuracy and superior performance for rare templates. However, existing methodologies suffer from significant limitations: flow cytometers are both costly and intricate, while fluorescence imaging relying on software tools or manual counting is time-consuming and prone…
▽ More
Absolute quantification of biological samples entails determining expression levels in precise numerical copies, offering enhanced accuracy and superior performance for rare templates. However, existing methodologies suffer from significant limitations: flow cytometers are both costly and intricate, while fluorescence imaging relying on software tools or manual counting is time-consuming and prone to inaccuracies. In this study, we have devised a comprehensive deep-learning-enabled pipeline that enables the automated segmentation and classification of GFP (green fluorescent protein)-labeled microreactors, facilitating real-time absolute quantification. Our findings demonstrate the efficacy of this technique in accurately predicting the sizes and occupancy status of microreactors using standard laboratory fluorescence microscopes, thereby providing precise measurements of template concentrations. Notably, our approach exhibits an analysis speed of quantifying over 2,000 microreactors (across 10 images) within remarkably 2.5 seconds, and a dynamic range spanning from 56.52 to 1569.43 copies per micron-liter. Furthermore, our Deep-dGFP algorithm showcases remarkable generalization capabilities, as it can be directly applied to various GFP-labeling scenarios, including droplet-based, microwell-based, and agarose-based biological applications. To the best of our knowledge, this represents the first successful implementation of an all-in-one image analysis algorithm in droplet digital PCR (polymerase chain reaction), microwell digital PCR, droplet single-cell sequencing, agarose digital PCR, and bacterial quantification, without necessitating any transfer learning steps, modifications, or retraining procedures. We firmly believe that our Deep-dGFP technique will be readily embraced by biomedical laboratories and holds potential for further development in related clinical applications.
△ Less
Submitted 4 September, 2023;
originally announced September 2023.
-
Investigation of W-SiC compositionally graded films as a divertor material
Authors:
Zihan Lin,
Carlos Monton,
Stefan Bringuier,
Gregory Sinclair,
Guangming Cheng,
Eduardo Marin,
Zachary Bergstrom,
Dmitry Rudakov,
Žana Popović,
Ulises Losada,
Igor Bykov,
Evan T. Ostrowski,
Shota Abe,
Nan Yao,
Bruce E. Koel,
Tyler Abrams
Abstract:
W-SiC composite material is a promising plasma-facing material candidate alternative to pure W due to the low neutron activation, low impurity radiation, and low tritium diffusivity of SiC while leveraging the high erosion resistance of the W armor. Additionally, W and SiC have high thermomechanical compatibility given their similar thermal expansion rates. The present study addresses the synthesi…
▽ More
W-SiC composite material is a promising plasma-facing material candidate alternative to pure W due to the low neutron activation, low impurity radiation, and low tritium diffusivity of SiC while leveraging the high erosion resistance of the W armor. Additionally, W and SiC have high thermomechanical compatibility given their similar thermal expansion rates. The present study addresses the synthesis and performance of compositionally graded W-SiC films fabricated by pulsed-DC magnetron sputtering. Compositional gradients were characterized using transmission electron microscopy (TEM) and energy-dispersive X-ray spectroscopy (EDS), and crystallographic information was obtained using electron diffraction and X-ray diffraction (XRD). Samples were exposed to L-mode deuterium plasma discharges in the DIII-D tokamak using the Divertor Material Evaluation System (DiMES). Post-mortem characterizations were performed using scanning electron microscopy (SEM) and XRD. Electron diffraction and XRD showed that the compositionally graded W-SiC films were composed of polycrystalline W and amorphous SiC with amorphous W+SiC interlayers. No macroscopic delamination or microstructural changes were observed under mild exposure conditions. This study serves as a preliminary examination of W-SiC compositionally graded composites as a potential candidate divertor material in future tokamak devices.
△ Less
Submitted 15 February, 2024; v1 submitted 30 August, 2023;
originally announced August 2023.
-
Small Object Detection via Coarse-to-fine Proposal Generation and Imitation Learning
Authors:
Xiang Yuan,
Gong Cheng,
Kebing Yan,
Qinghua Zeng,
Junwei Han
Abstract:
The past few years have witnessed the immense success of object detection, while current excellent detectors struggle on tackling size-limited instances. Concretely, the well-known challenge of low overlaps between the priors and object regions leads to a constrained sample pool for optimization, and the paucity of discriminative information further aggravates the recognition. To alleviate the afo…
▽ More
The past few years have witnessed the immense success of object detection, while current excellent detectors struggle on tackling size-limited instances. Concretely, the well-known challenge of low overlaps between the priors and object regions leads to a constrained sample pool for optimization, and the paucity of discriminative information further aggravates the recognition. To alleviate the aforementioned issues, we propose CFINet, a two-stage framework tailored for small object detection based on the Coarse-to-fine pipeline and Feature Imitation learning. Firstly, we introduce Coarse-to-fine RPN (CRPN) to ensure sufficient and high-quality proposals for small objects through the dynamic anchor selection strategy and cascade regression. Then, we equip the conventional detection head with a Feature Imitation (FI) branch to facilitate the region representations of size-limited instances that perplex the model in an imitation manner. Moreover, an auxiliary imitation loss following supervised contrastive learning paradigm is devised to optimize this branch. When integrated with Faster RCNN, CFINet achieves state-of-the-art performance on the large-scale small object detection benchmarks, SODA-D and SODA-A, underscoring its superiority over baseline detector and other mainstream detection approaches.
△ Less
Submitted 18 August, 2023;
originally announced August 2023.
-
Alternative Pseudo-Labeling for Semi-Supervised Automatic Speech Recognition
Authors:
Han Zhu,
Dongji Gao,
Gaofeng Cheng,
Daniel Povey,
Pengyuan Zhang,
Yonghong Yan
Abstract:
When labeled data is insufficient, semi-supervised learning with the pseudo-labeling technique can significantly improve the performance of automatic speech recognition. However, pseudo-labels are often noisy, containing numerous incorrect tokens. Taking noisy labels as ground-truth in the loss function results in suboptimal performance. Previous works attempted to mitigate this issue by either fi…
▽ More
When labeled data is insufficient, semi-supervised learning with the pseudo-labeling technique can significantly improve the performance of automatic speech recognition. However, pseudo-labels are often noisy, containing numerous incorrect tokens. Taking noisy labels as ground-truth in the loss function results in suboptimal performance. Previous works attempted to mitigate this issue by either filtering out the nosiest pseudo-labels or improving the overall quality of pseudo-labels. While these methods are effective to some extent, it is unrealistic to entirely eliminate incorrect tokens in pseudo-labels. In this work, we propose a novel framework named alternative pseudo-labeling to tackle the issue of noisy pseudo-labels from the perspective of the training objective. The framework comprises several components. Firstly, a generalized CTC loss function is introduced to handle noisy pseudo-labels by accepting alternative tokens in the positions of incorrect tokens. Applying this loss function in pseudo-labeling requires detecting incorrect tokens in the predicted pseudo-labels. In this work, we adopt a confidence-based error detection method that identifies the incorrect tokens by comparing their confidence scores with a given threshold, thus necessitating the confidence score to be discriminative. Hence, the second proposed technique is the contrastive CTC loss function that widens the confidence gap between the correctly and incorrectly predicted tokens, thereby improving the error detection ability. Additionally, obtaining satisfactory performance with confidence-based error detection typically requires extensive threshold tuning. Instead, we propose an automatic thresholding method that uses labeled data as a proxy for determining the threshold, thus saving the pain of manual tuning.
△ Less
Submitted 12 August, 2023;
originally announced August 2023.