Shujian Yu
YOU?
Author Swipe
View article: Higher‐Order Triadic Interactions: Insights Into the Multiscale Network Organization in Schizophrenia
Higher‐Order Triadic Interactions: Insights Into the Multiscale Network Organization in Schizophrenia Open
Complex biological systems, like the brain, exhibit intricate multiway and multiscale interactions that drive emergent behaviors. In psychiatry, neural processes extend beyond pairwise connectivity, involving higher‐order interactions crit…
View article: BrainIB++: Leveraging graph neural networks and information bottleneck for functional brain biomarkers in schizophrenia
BrainIB++: Leveraging graph neural networks and information bottleneck for functional brain biomarkers in schizophrenia Open
View article: Adapting HFMCA to Graph Data: Self-Supervised Learning for Generalizable fMRI Representations
Adapting HFMCA to Graph Data: Self-Supervised Learning for Generalizable fMRI Representations Open
Functional magnetic resonance imaging (fMRI) analysis faces significant challenges due to limited dataset sizes and domain variability between studies. Traditional self-supervised learning methods inspired by computer vision often rely on …
View article: Efficient Brain Network Estimation with Sparse ICA in Non-Human Primate Neuroimaging
Efficient Brain Network Estimation with Sparse ICA in Non-Human Primate Neuroimaging Open
Independent component analysis (ICA) is widely used to separate mixed signals and recover statistically independent components. However, in non-human primate neuroimaging studies, most ICA-recovered spatial maps are often dense. To extract…
View article: MvHo-IB: Multi-view Higher-Order Information Bottleneck for Brain Disorder Diagnosis
MvHo-IB: Multi-view Higher-Order Information Bottleneck for Brain Disorder Diagnosis Open
View article: Dual-Alignment Knowledge Retention for Continual Medical Image Segmentation
Dual-Alignment Knowledge Retention for Continual Medical Image Segmentation Open
Continual learning in medical image segmentation involves sequential data acquisition across diverse domains (e.g., clinical sites), where task interference between past and current domains often leads to catastrophic forgetting. Existing …
View article: InfoDPCCA: Information-Theoretic Dynamic Probabilistic Canonical Correlation Analysis
InfoDPCCA: Information-Theoretic Dynamic Probabilistic Canonical Correlation Analysis Open
Extracting meaningful latent representations from high-dimensional sequential data is a crucial challenge in machine learning, with applications spanning natural science and engineering. We introduce InfoDPCCA, a dynamic probabilistic Cano…
View article: Aggregation of Dependent Expert Distributions in Multimodal Variational Autoencoders
Aggregation of Dependent Expert Distributions in Multimodal Variational Autoencoders Open
Multimodal learning with variational autoencoders (VAEs) requires estimating joint distributions to evaluate the evidence lower bound (ELBO). Current methods, the product and mixture of experts, aggregate single-modality distributions assu…
View article: Beyond Pairwise Connections in Complex Systems: Insights into the Human Multiscale Psychotic Brain
Beyond Pairwise Connections in Complex Systems: Insights into the Human Multiscale Psychotic Brain Open
Complex biological systems, like the brain, exhibit intricate multiway and multiscale interactions that drive emergent behaviors. In psychiatry, neural processes extend beyond pairwise connectivity, involving higher-order interactions crit…
View article: The Conditional Cauchy-Schwarz Divergence With Applications to Time-Series Data and Sequential Decision Making
The Conditional Cauchy-Schwarz Divergence With Applications to Time-Series Data and Sequential Decision Making Open
The Cauchy-Schwarz (CS) divergence was developed by Príncipe et al. in 2000. In this paper, we extend the classic CS divergence to quantify the closeness between two conditional distributions and show that the developed conditional CS dive…
View article: An information bottleneck approach for feature selection
An information bottleneck approach for feature selection Open
View article: A Hierarchical Taxonomy For Deep State Space Models
A Hierarchical Taxonomy For Deep State Space Models Open
Modeling nonlinear dynamical systems is a challenging task in fields such as speech processing, music generation, and video prediction. This paper introduces a hierarchical framework for Deep State Space Models (DSSMs), categorizing them b…
View article: Deep Dynamic Probabilistic Canonical Correlation Analysis
Deep Dynamic Probabilistic Canonical Correlation Analysis Open
This paper presents Deep Dynamic Probabilistic Canonical Correlation Analysis (D2PCCA), a model that integrates deep learning with probabilistic modeling to analyze nonlinear dynamical systems. Building on the probabilistic exte…
View article: Cauchy-Schwarz Divergence Transfer Entropy
Cauchy-Schwarz Divergence Transfer Entropy Open
Transfer entropy (TE) is a powerful information-theoretic tool for analyzing causality in time series and complex systems. In this work, we propose a new formulation of TE using the Cauchy-Schwarz (CS) divergence. The resulting CS-TE offer…
View article: Distributional Vision-Language Alignment by Cauchy-Schwarz Divergence
Distributional Vision-Language Alignment by Cauchy-Schwarz Divergence Open
Multimodal alignment is crucial for various downstream tasks such as cross-modal generation and retrieval. Previous multimodal approaches like CLIP utilize InfoNCE to maximize mutual information, primarily aligning pairwise samples across …
View article: A unified model integrating Granger causality-based causal discovery and fault diagnosis in chemical processes
A unified model integrating Granger causality-based causal discovery and fault diagnosis in chemical processes Open
View article: Deep Dynamic Probabilistic Canonical Correlation Analysis
Deep Dynamic Probabilistic Canonical Correlation Analysis Open
This paper presents Deep Dynamic Probabilistic Canonical Correlation Analysis (D2PCCA), a model that integrates deep learning with probabilistic modeling to analyze nonlinear dynamical systems. Building on the probabilistic extensions of C…
View article: Guest Editorial: Special Issue on Information Theoretic Methods for the Generalization, Robustness, and Interpretability of Machine Learning
Guest Editorial: Special Issue on Information Theoretic Methods for the Generalization, Robustness, and Interpretability of Machine Learning Open
View article: Towards the Generalization of Multi-view Learning: An Information-theoretical Analysis
Towards the Generalization of Multi-view Learning: An Information-theoretical Analysis Open
Multiview learning has drawn widespread attention for its efficacy in leveraging cross-view consensus and complementarity information to achieve a comprehensive representation of data. While multi-view learning has undergone vigorous devel…
View article: ELEMENT: Episodic and Lifelong Exploration via Maximum Entropy
ELEMENT: Episodic and Lifelong Exploration via Maximum Entropy Open
This paper proposes \emph{Episodic and Lifelong Exploration via Maximum ENTropy} (ELEMENT), a novel, multiscale, intrinsically motivated reinforcement learning (RL) framework that is able to explore environments without using any extrinsic…
View article: Incipient fault detection and isolation with Cauchy–Schwarz divergence: A probabilistic approach
Incipient fault detection and isolation with Cauchy–Schwarz divergence: A probabilistic approach Open
To monitor the dynamics and non-stationarity inherent in industrial processes, we propose a novel incipient fault detection and isolation scheme grounded in a probabilistic perspective, using the Cauchy–Schwarz (CS) divergence. Our innovat…
View article: Discovering Common Information in Multi-view Data
Discovering Common Information in Multi-view Data Open
We introduce an innovative and mathematically rigorous definition for computing common information from multi-view data, drawing inspiration from Gács-Körner common information in information theory. Leveraging this definition, we develop …
View article: BAN: Detecting Backdoors Activated by Adversarial Neuron Noise
BAN: Detecting Backdoors Activated by Adversarial Neuron Noise Open
Backdoor attacks on deep learning represent a recent threat that has gained significant attention in the research community. Backdoor defenses are mainly based on backdoor inversion, which has been shown to be generic, model-agnostic, and …
View article: Domain Adaptation with Cauchy-Schwarz Divergence
Domain Adaptation with Cauchy-Schwarz Divergence Open
Domain adaptation aims to use training data from one or multiple source domains to learn a hypothesis that can be generalized to a different, but related, target domain. As such, having a reliable measure for evaluating the discrepancy of …
View article: Jacobian Regularizer-based Neural Granger Causality
Jacobian Regularizer-based Neural Granger Causality Open
With the advancement of neural networks, diverse methods for neural Granger causality have emerged, which demonstrate proficiency in handling complex data, and nonlinear relationships. However, the existing framework of neural Granger caus…
View article: Generalized Cauchy-Schwarz Divergence and Its Deep Learning Applications
Generalized Cauchy-Schwarz Divergence and Its Deep Learning Applications Open
Divergence measures play a central role and become increasingly essential in deep learning, yet efficient measures for multiple (more than two) distributions are rarely explored. This becomes particularly crucial in areas where the simulta…
View article: Cauchy-Schwarz Divergence Information Bottleneck for Regression
Cauchy-Schwarz Divergence Information Bottleneck for Regression Open
The information bottleneck (IB) approach is popular to improve the generalization, robustness and explainability of deep neural networks. Essentially, it aims to find a minimum sufficient representation $\mathbf{t}$ by striking a trade-off…
View article: Discovering common information in multi-view data
Discovering common information in multi-view data Open
View article: BPI-GNN: Interpretable brain network-based psychiatric diagnosis and subtyping
BPI-GNN: Interpretable brain network-based psychiatric diagnosis and subtyping Open
View article: DIB-X: Formulating Explainability Principles for a Self-Explainable Model Through Information Theoretic Learning
DIB-X: Formulating Explainability Principles for a Self-Explainable Model Through Information Theoretic Learning Open
The recent development of self-explainable deep learning approaches has focused on integrating well-defined explainability principles into learning process, with the goal of achieving these principles through optimization. In this work, we…