arXiv subjects

Shihua Zhang

Publications and source records attributed to Shihua Zhang.

At least 37 records · Page 2Linked to original sources

arXiv2024

Progressive Feedforward Collapse of ResNet Training

Neural collapse (NC) is a simple and symmetric phenomenon for deep neural networks (DNNs) at the terminal phase of training, where the last-layer features collapse to their class means and form a simplex equiangular tight frame aligning with the classifier vectors. However, the relationship of the last-layer features to the data and intermediate layers during training remains unexplored. To this end, we characterize the geometry of intermediate layers of ResNet and propose a novel conjecture, progressive feedforward collapse (PFC), claiming the degree of collapse increases during the forward propagation of DNNs. We derive a transparent model for the well-trained ResNet according to that ResNet with weight decay approximates the geodesic curve in Wasserstein space at the terminal phase. The metrics of PFC indeed monotonically decrease across depth on various datasets. We propose a new surrogate model, multilayer unconstrained feature model (MUFM), connecting intermediate layers by an optimal transport regularizer. The optimal solution of MUFM is inconsistent with NC but is more concentrated relative to the input data. Overall, this study extends NC to PFC to model the collapse phenomenon of intermediate layers and its dependence on the input data, shedding light on the theoretical understanding of ResNet in classification problems.

cs.LG↗

arXiv2022

Information-theoretic Classification Accuracy: A Criterion that Guides Data-driven Combination of Ambiguous Outcome Labels in Multi-class Classification

Outcome labeling ambiguity and subjectivity are ubiquitous in real-world datasets. While practitioners commonly combine ambiguous outcome labels for all data points (instances) in an ad hoc way to improve the accuracy of multi-class classification, there lacks a principled approach to guide the label combination for all data points by any optimality criterion. To address this problem, we propose the information-theoretic classification accuracy (ITCA), a criterion that balances the trade-off between prediction accuracy (how well do predicted labels agree with actual labels) and classification resolution (how many labels are predictable), to guide practitioners on how to combine ambiguous outcome labels. To find the optimal label combination indicated by ITCA, we propose two search strategies: greedy search and breadth-first search. Notably, ITCA and the two search strategies are adaptive to all machine-learning classification algorithms. Coupled with a classification algorithm and a search strategy, ITCA has two uses: improving prediction accuracy and identifying ambiguous labels. We first verify that ITCA achieves high accuracy with both search strategies in finding the correct label combinations on synthetic and real data. Then we demonstrate the effectiveness of ITCA in diverse applications including medical prognosis, cancer survival prediction, user demographics prediction, and cell type classification. We also provide theoretical insights into ITCA by studying the oracle and the linear discriminant analysis classification algorithms. Python package itca (available at https://github.com/JSB-UCLA/ITCA) implements ITCA and search strategies.

stat.ML↗

arXiv2021

Rethinking Influence Functions of Neural Networks in the Over-parameterized Regime

Understanding the black-box prediction for neural networks is challenging. To achieve this, early studies have designed influence function (IF) to measure the effect of removing a single training point on neural networks. However, the classic implicit Hessian-vector product (IHVP) method for calculating IF is fragile, and theoretical analysis of IF in the context of neural networks is still lacking. To this end, we utilize the neural tangent kernel (NTK) theory to calculate IF for the neural network trained with regularized mean-square loss, and prove that the approximation error can be arbitrarily small when the width is sufficiently large for two-layer ReLU networks. We analyze the error bound for the classic IHVP method in the over-parameterized regime to understand when and why it fails or not. In detail, our theoretical analysis reveals that (1) the accuracy of IHVP depends on the regularization term, and is pretty low under weak regularization; (2) the accuracy of IHVP has a significant correlation with the probability density of corresponding training points. We further borrow the theory from NTK to understand the IFs better, including quantifying the complexity for influential samples and depicting the variation of IFs during the training dynamics. Numerical experiments on real-world data confirm our theoretical results and demonstrate our findings.

cs.LG↗

arXiv2021

Tessellated Wasserstein Auto-Encoders

Non-adversarial generative models such as variational auto-encoder (VAE), Wasserstein auto-encoders with maximum mean discrepancy (WAE-MMD), sliced-Wasserstein auto-encoder (SWAE) are relatively easy to train and have less mode collapse compared to Wasserstein auto-encoder with generative adversarial network (WAE-GAN). However, they are not very accurate in approximating the target distribution in the latent space because they don't have a discriminator to detect the minor difference between real and fake. To this end, we develop a novel non-adversarial framework called Tessellated Wasserstein Auto-encoders (TWAE) to tessellate the support of the target distribution into a given number of regions by the centroidal Voronoi tessellation (CVT) technique and design batches of data according to the tessellation instead of random shuffling for accurate computation of discrepancy. Theoretically, we demonstrate that the error of estimate to the discrepancy decreases when the numbers of samples $n$ and regions $m$ of the tessellation become larger with rates of $\mathcal{O}(\frac{1}{\sqrt{n}})$ and $\mathcal{O}(\frac{1}{\sqrt{m}})$, respectively. Given fixed $n$ and $m$, a necessary condition for the upper bound of measurement error to be minimized is that the tessellation is the one determined by CVT. TWAE is very flexible to different non-adversarial metrics and can substantially enhance their generative performance in terms of Fréchet inception distance (FID) compared to VAE, WAE-MMD, SWAE. Moreover, numerical results indeed demonstrate that TWAE is competitive to the adversarial model WAE-GAN, demonstrating its powerful generative ability.

stat.ML↗

arXiv2021

Adversarial Information Bottleneck

The information bottleneck (IB) principle has been adopted to explain deep learning in terms of information compression and prediction, which are balanced by a trade-off hyperparameter. How to optimize the IB principle for better robustness and figure out the effects of compression through the trade-off hyperparameter are two challenging problems. Previous methods attempted to optimize the IB principle by introducing random noise into learning the representation and achieved state-of-the-art performance in the nuisance information compression and semantic information extraction. However, their performance on resisting adversarial perturbations is far less impressive. To this end, we propose an adversarial information bottleneck (AIB) method without any explicit assumptions about the underlying distribution of the representations, which can be optimized effectively by solving a Min-Max optimization problem. Numerical experiments on synthetic and real-world datasets demonstrate its effectiveness on learning more invariant representations and mitigating adversarial perturbations compared to several competing IB methods. In addition, we analyse the adversarial robustness of diverse IB methods contrasting with their IB curves, and reveal that IB models with the hyperparameter $β$ corresponding to the knee point in the IB curve achieve the best trade-off between compression and prediction, and has best robustness against various attacks.

cs.LG↗

arXiv2021

Matrix Normal PCA for Interpretable Dimension Reduction and Graphical Noise Modeling

Principal component analysis (PCA) is one of the most widely used dimension reduction and multivariate statistical techniques. From a probabilistic perspective, PCA seeks a low-dimensional representation of data in the presence of independent identical Gaussian noise. Probabilistic PCA (PPCA) and its variants have been extensively studied for decades. Most of them assume the underlying noise follows a certain independent identical distribution. However, the noise in the real world is usually complicated and structured. To address this challenge, some variants of PCA for data with non-IID noise have been proposed. However, most of the existing methods only assume that the noise is correlated in the feature space while there may exist two-way structured noise. To this end, we propose a powerful and intuitive PCA method (MN-PCA) through modeling the graphical noise by the matrix normal distribution, which enables us to explore the structure of noise in both the feature space and the sample space. MN-PCA obtains a low-rank representation of data and the structure of noise simultaneously. And it can be explained as approximating data over the generalized Mahalanobis distance. We develop two algorithms to solve this model: one maximizes the regularized likelihood, the other exploits the Wasserstein distance, which is more robust. Extensive experiments on various data demonstrate their effectiveness.

cs.LG↗

arXiv2020

Learnable Graph-regularization for Matrix Decomposition

Low-rank approximation models of data matrices have become important machine learning and data mining tools in many fields including computer vision, text mining, bioinformatics and many others. They allow for embedding high-dimensional data into low-dimensional spaces, which mitigates the effects of noise and uncovers latent relations. In order to make the learned representations inherit the structures in the original data, graph-regularization terms are often added to the loss function. However, the prior graph construction often fails to reflect the true network connectivity and the intrinsic relationships. In addition, many graph-regularized methods fail to take the dual spaces into account. Probabilistic models are often used to model the distribution of the representations, but most of previous methods often assume that the hidden variables are independent and identically distributed for simplicity. To this end, we propose a learnable graph-regularization model for matrix decomposition (LGMD), which builds a bridge between graph-regularized methods and probabilistic matrix decomposition models. LGMD learns two graphical structures (i.e., two precision matrices) in real-time in an iterative manner via sparse precision matrix estimation and is more robust to noise and missing entries. Extensive numerical results and comparison with competing methods demonstrate its effectiveness.

cs.LG↗

arXiv2020

Distributed Bayesian Matrix Decomposition for Big Data Mining and Clustering

Matrix decomposition is one of the fundamental tools to discover knowledge from big data generated by modern applications. However, it is still inefficient or infeasible to process very big data using such a method in a single machine. Moreover, big data are often distributedly collected and stored on different machines. Thus, such data generally bear strong heterogeneous noise. It is essential and useful to develop distributed matrix decomposition for big data analytics. Such a method should scale up well, model the heterogeneous noise, and address the communication issue in a distributed system. To this end, we propose a distributed Bayesian matrix decomposition model (DBMD) for big data mining and clustering. Specifically, we adopt three strategies to implement the distributed computing including 1) the accelerated gradient descent, 2) the alternating direction method of multipliers (ADMM), and 3) the statistical inference. We investigate the theoretical convergence behaviors of these algorithms. To address the heterogeneity of the noise, we propose an optimal plug-in weighted average that reduces the variance of the estimation. Synthetic experiments validate our theoretical results, and real-world experiments show that our algorithms scale up well to big data and achieves superior or competing performance compared to other distributed methods.

cs.LG↗

arXiv2019

Towards Understanding Residual and Dilated Dense Neural Networks via Convolutional Sparse Coding

Convolutional neural network (CNN) and its variants have led to many state-of-art results in various fields. However, a clear theoretical understanding about them is still lacking. Recently, multi-layer convolutional sparse coding (ML-CSC) has been proposed and proved to equal such simply stacked networks (plain networks). Here, we think three factors in each layer of it including the initialization, the dictionary design and the number of iterations greatly affect the performance of ML-CSC. Inspired by these considerations, we propose two novel multi-layer models--residual convolutional sparse coding model (Res-CSC) and mixed-scale dense convolutional sparse coding model (MSD-CSC), which have close relationship with the residual neural network (ResNet) and mixed-scale (dilated) dense neural network (MSDNet), respectively. Mathematically, we derive the shortcut connection in ResNet as a special case of a new forward propagation rule on ML-CSC. We find a theoretical interpretation of the dilated convolution and dense connection in MSDNet by analyzing MSD-CSC, which gives a clear mathematical understanding about them. We implement the iterative soft thresholding algorithm (ISTA) and its fast version to solve Res-CSC and MSD-CSC, which can employ the unfolding operation for further improvements. At last, extensive numerical experiments and comparison with competing methods demonstrate their effectiveness using three typical datasets.

cs.LG↗

arXiv2018

Group-sparse SVD Models and Their Applications in Biological Data

Sparse Singular Value Decomposition (SVD) models have been proposed for biclustering high dimensional gene expression data to identify block patterns with similar expressions. However, these models do not take into account prior group effects upon variable selection. To this end, we first propose group-sparse SVD models with group Lasso (GL1-SVD) and group L0-norm penalty (GL0-SVD) for non-overlapping group structure of variables. However, such group-sparse SVD models limit their applicability in some problems with overlapping structure. Thus, we also propose two group-sparse SVD models with overlapping group Lasso (OGL1-SVD) and overlapping group L0-norm penalty (OGL0-SVD). We first adopt an alternating iterative strategy to solve GL1-SVD based on a block coordinate descent method, and GL0-SVD based on a projection method. The key of solving OGL1-SVD is a proximal operator with overlapping group Lasso penalty. We employ an alternating direction method of multipliers (ADMM) to solve the proximal operator. Similarly, we develop an approximate method to solve OGL0-SVD. Applications of these methods and comparison with competing ones using simulated data demonstrate their effectiveness. Extensive applications of them onto several real gene expression data with gene prior group knowledge identify some biologically interpretable gene modules.

stat.ML↗

arXiv2017

Bayesian Joint Matrix Decomposition for Data Integration with Heterogeneous Noise

Matrix decomposition is a popular and fundamental approach in machine learning and data mining. It has been successfully applied into various fields. Most matrix decomposition methods focus on decomposing a data matrix from one single source. However, it is common that data are from different sources with heterogeneous noise. A few of matrix decomposition methods have been extended for such multi-view data integration and pattern discovery. While only few methods were designed to consider the heterogeneity of noise in such multi-view data for data integration explicitly. To this end, we propose a joint matrix decomposition framework (BJMD), which models the heterogeneity of noise by Gaussian distribution in a Bayesian framework. We develop two algorithms to solve this model: one is a variational Bayesian inference algorithm, which makes full use of the posterior distribution; and another is a maximum a posterior algorithm, which is more scalable and can be easily paralleled. Extensive experiments on synthetic and real-world datasets demonstrate that BJMD considering the heterogeneity of noise is superior or competitive to the state-of-the-art methods.

cs.CV↗

arXiv2017

MSIQ: Joint Modeling of Multiple RNA-seq Samples for Accurate Isoform Quantification

Next-generation RNA sequencing (RNA-seq) technology has been widely used to assess full-length RNA isoform abundance in a high-throughput manner. RNA-seq data offer insight into gene expression levels and transcriptome structures, enabling us to better understand the regulation of gene expression and fundamental biological processes. Accurate isoform quantification from RNA-seq data is challenging due to the information loss in sequencing experiments. A recent accumulation of multiple RNA-seq data sets from the same tissue or cell type provides new opportunities to improve the accuracy of isoform quantification. However, existing statistical or computational methods for multiple RNA-seq samples either pool the samples into one sample or assign equal weights to the samples when estimating isoform abundance. These methods ignore the possible heterogeneity in the quality of different samples and could result in biased and unrobust estimates. In this article, we develop a method, which we call "joint modeling of multiple RNA-seq samples for accurate isoform quantification" (MSIQ), for more accurate and robust isoform quantification by integrating multiple RNA-seq samples under a Bayesian framework. Our method aims to (1) identify a consistent group of samples with homogeneous quality and (2) improve isoform quantification accuracy by jointly modeling multiple RNA-seq samples by allowing for higher weights on the consistent group. We show that MSIQ provides a consistent estimator of isoform abundance, and we demonstrate the accuracy and effectiveness of MSIQ compared with alternative methods through simulation studies on D. melanogaster genes. We justify MSIQ's advantages over existing approaches via application studies on real RNA-seq data from human embryonic stem cells, brain tissues, and the HepG2 immortalized cell line.

stat.AP↗

arXiv2017

Sparse Weighted Canonical Correlation Analysis

Given two data matrices $X$ and $Y$, sparse canonical correlation analysis (SCCA) is to seek two sparse canonical vectors $u$ and $v$ to maximize the correlation between $Xu$ and $Yv$. However, classical and sparse CCA models consider the contribution of all the samples of data matrices and thus cannot identify an underlying specific subset of samples. To this end, we propose a novel sparse weighted canonical correlation analysis (SWCCA), where weights are used for regularizing different samples. We solve the $L_0$-regularized SWCCA ($L_0$-SWCCA) using an alternating iterative algorithm. We apply $L_0$-SWCCA to synthetic data and real-world data to demonstrate its effectiveness and superiority compared to related methods. Lastly, we consider also SWCCA with different penalties like LASSO (Least absolute shrinkage and selection operator) and Group LASSO, and extend it for integrating more than three data matrices.

cs.LG↗

arXiv2017

Sparse Deep Nonnegative Matrix Factorization

Nonnegative matrix factorization is a powerful technique to realize dimension reduction and pattern recognition through single-layer data representation learning. Deep learning, however, with its carefully designed hierarchical structure, is able to combine hidden features to form more representative features for pattern recognition. In this paper, we proposed sparse deep nonnegative matrix factorization models to analyze complex data for more accurate classification and better feature interpretation. Such models are designed to learn localized features or generate more discriminative representations for samples in distinct classes by imposing $L_1$-norm penalty on the columns of certain factors. By extending one-layer model into multi-layer one with sparsity, we provided a hierarchical way to analyze big data and extract hidden features intuitively due to nonnegativity. We adopted the Nesterov's accelerated gradient algorithm to accelerate the computing process with the convergence rate of $O(1/k^2)$ after $k$ steps iteration. We also analyzed the computing complexity of our framework to demonstrate their efficiency. To improve the performance of dealing with linearly inseparable data, we also considered to incorporate popular nonlinear functions into this framework and explored their performance. We applied our models onto two benchmarking image datasets, demonstrating our models can achieve competitive or better classification performance and produce intuitive interpretations compared with the typical NMF and competing multi-layer models.

cs.CV↗

arXiv2017

A Unified Joint Matrix Factorization Framework for Data Integration

Nonnegative matrix factorization (NMF) is a powerful tool in data exploratory analysis by discovering the hidden features and part-based patterns from high-dimensional data. NMF and its variants have been successfully applied into diverse fields such as pattern recognition, signal processing, data mining, bioinformatics and so on. Recently, NMF has been extended to analyze multiple matrices simultaneously. However, a unified framework is still lacking. In this paper, we introduce a sparse multiple relationship data regularized joint matrix factorization (JMF) framework and two adapted prediction models for pattern recognition and data integration. Next, we present four update algorithms to solve this framework. The merits and demerits of these algorithms are systematically explored. Furthermore, extensive computational experiments using both synthetic data and real data demonstrate the effectiveness of JMF framework and related algorithms on pattern recognition and data mining.

cs.CV↗

arXiv2016

Discovery of cancer common and specific driver gene sets

Cancer is known as a disease mainly caused by gene alterations. Discovery of mutated driver pathways or gene sets is becoming an important step to understand molecular mechanisms of carcinogenesis. However, systematically investigating commonalities and specificities of driver gene sets among multiple cancer types is still a great challenge, but this investigation will undoubtedly benefit deciphering cancers and will be helpful for personalized therapy and precision medicine in cancer treatment. In this study, we propose two optimization models to \emph{de novo} discover common driver gene sets among multiple cancer types (ComMDP) and specific driver gene sets of one certain or multiple cancer types to other cancers (SpeMDP), respectively. We first apply ComMDP and SpeMDP to simulated data to validate their efficiency. Then, we further apply these methods to 12 cancer types from The Cancer Genome Atlas (TCGA) and obtain several biologically meaningful driver pathways. As examples, we construct a common cancer pathway model for BRCA and OV, infer a complex driver pathway model for BRCA carcinogenesis based on common driver gene sets of BRCA with eight cancer types, and investigate specific driver pathways of the liquid cancer lymphoblastic acute myeloid leukemia (LAML) versus other solid cancer types. In these processes more candidate cancer genes are also found.

q-bio.GN↗

arXiv2016

Network-regularized Sparse Logistic Regression Models for Clinical Risk Prediction and Biomarker Discovery

Molecular profiling data (e.g., gene expression) has been used for clinical risk prediction and biomarker discovery. However, it is necessary to integrate other prior knowledge like biological pathways or gene interaction networks to improve the predictive ability and biological interpretability of biomarkers. Here, we first introduce a general regularized Logistic Regression (LR) framework with regularized term $λ\|\bm{w}\|_1 + η\bm{w}^T\bm{M}\bm{w}$, which can reduce to different penalties, including Lasso, elastic net, and network-regularized terms with different $\bm{M}$. This framework can be easily solved in a unified manner by a cyclic coordinate descent algorithm which can avoid inverse matrix operation and accelerate the computing speed. However, if those estimated $\bm{w}_i$ and $\bm{w}_j$ have opposite signs, then the traditional network-regularized penalty may not perform well. To address it, we introduce a novel network-regularized sparse LR model with a new penalty $λ\|\bm{w}\|_1 + η|\bm{w}|^T\bm{M}|\bm{w}|$ to consider the difference between the absolute values of the coefficients. And we develop two efficient algorithms to solve it. Finally, we test our methods and compare them with the related ones using simulated and real data to show their efficiency.

q-bio.GN↗

arXiv2016

The Discovery of Mutated Driver Pathways in Cancer: Models and Algorithms

The pathogenesis of cancer in human is still poorly understood. With the rapid development of high-throughput sequencing technologies, huge volumes of cancer genomics data have been generated. Deciphering those data poses great opportunities and challenges to computational biologists. One of such key challenges is to distinguish driver mutations, genes as well as pathways from passenger ones. Mutual exclusivity of gene mutations (each patient has no more than one mutation in the gene set) has been observed in various cancer types and thus has been used as an important property of a driver gene set or pathway. In this article, we aim to review the recent development of computational models and algorithms for discovering driver pathways or modules in cancer with the focus on mutual exclusivity-based ones.

q-bio.GN↗