25 citations · 85 across the 36 of their papers we have counts for
37 papers
Fair Multi-View Determinantal Coresets via Adaptive NEPv
Richard Yi Da Xu
Selecting a small, diverse subset from a large candidate pool often means balancing several incompatible notions of diversity. In trademark curation, for instance, a subset should…
Hierarchical Copula-Gumbel-Top-K Routing: Two-Sided Dependence Control for Frozen Mixture-of-Experts at Fixed Per-Token Routing Laws
Richard Yi Da Xu
A stochastic Gumbel-Top-K router defines, for every token of a mixture-of-experts (MoE) model, a routing law: a distribution over ordered expert lists and mixture weights. We ask w…
Spectral Certificates and Projection-DPP Rounding for Determinantal MAP Selection
Richard Yi Da Xu
Selecting a fixed-size subset that maximizes the determinant of a positive semidefinite kernel is the MAP problem for a size-constrained determinantal point process and the classic…
Rethinking Generalization in Graph Neural Networks: A Structural Complexity Perspective
Peiyao Wang, Liang Bai, Xian Yang +2
Graph neural networks (GNNs) have emerged as a fundamental tool for learning from graph-structured data, achieving strong performance across a wide range of applications. However,…
TsCA: On the Semantic Consistency Alignment via Conditional Transport for Compositional Zero-Shot Learning
Miaoge Li, Jingcai Guo, Richard Yi Da Xu +4
Compositional Zero-Shot Learning (CZSL) aims to recognize novel state-object compositions by leveraging the shared knowledge of their primitive components. Despite considerable pro…
Nonlinear Eigen-approach ADMM for Sparse Optimization on Stiefel Manifold
Jiawei Wang, Rencang Li, Richard Yi Da Xu
With the growing interest and applications in machine learning and data science, finding an efficient method to sparse analysis the high-dimensional data and optimizing a dimension…
KERMIT: Knowledge Graph Completion of Enhanced Relation Modeling with Inverse Transformation
Haotian Li, Bin Yu, Yuliang Wei +3
Knowledge graph completion (KGC) revolves around populating missing triples in a knowledge graph using available information. Text-based methods, which depend on textual descriptio…
A variational autoencoder-based nonnegative matrix factorisation model for deep dictionary learning
Hong-Bo Xie, Caoyuan Li, Shuliang Wang +2
Construction of dictionaries using nonnegative matrix factorisation (NMF) has extensive applications in signal processing and machine learning. With the advances in deep learning,…
Free Lunch for Generating Effective Outlier Supervision
Sen Pei, Jiaxi Sun, Richard Yi Da Xu +3
When deployed in practical applications, computer vision systems will encounter numerous unexpected images (\emph{i.e.}, out-of-distribution data). Due to the potentially raised sa…
Demystify Self-Attention in Vision Transformers from a Semantic Perspective: Analysis and Application
Leijie Wu, Song Guo, Yaohong Ding +4
Self-attention mechanisms, especially multi-head self-attention (MSA), have achieved great success in many fields such as computer vision and natural language processing. However,…
Domain Decorrelation with Potential Energy Ranking
Sen Pei, Jiaxi Sun, Richard Yi Da Xu +2
Machine learning systems, especially the methods based on deep learning, enjoy great success in modern computer vision tasks under experimental settings. Generally, these classic d…
Demystify Optimization and Generalization of Over-parameterized PAC-Bayesian Learning
Wei Huang, Chunrui Liu, Yilan Chen +2
PAC-Bayesian is an analysis framework where the training error can be expressed as the weighted average of the hypotheses in the posterior distribution whilst incorporating the pri…
Regularize! Don't Mix: Multi-Agent Reinforcement Learning without Explicit Centralized Structures
Chapman Siu, Jason Traish, Richard Yi Da Xu
We propose using regularization for Multi-Agent Reinforcement Learning rather than learning explicit cooperative structures called {\em Multi-Agent Regularized Q-learning} (MARQ).…
Dual Behavior Regularized Reinforcement Learning
Chapman Siu, Jason Traish, Richard Yi Da Xu
Reinforcement learning has been shown to perform a range of complex tasks through interaction with an environment or collected leveraging experience. However, many of these approac…
Greedy UnMixing for Q-Learning in Multi-Agent Reinforcement Learning
Chapman Siu, Jason Traish, Richard Yi Da Xu
This paper introduces Greedy UnMix (GUM) for cooperative multi-agent reinforcement learning (MARL). Greedy UnMix aims to avoid scenarios where MARL methods fail due to overestimati…
Alleviating Mode Collapse in GAN via Diversity Penalty Module
Sen Pei, Richard Yi Da Xu, Shiming Xiang +1
The vanilla GAN (Goodfellow et al. 2014) suffers from mode collapse deeply, which usually manifests as that the images generated by generators tend to have a high similarity amongs…
Towards Deepening Graph Neural Networks: A GNTK-based Optimization Perspective
Wei Huang, Yayong Li, Weitao Du +4
Graph convolutional networks (GCNs) and their variants have achieved great success in dealing with graph-structured data. Nevertheless, it is well known that deep GCNs suffer from…
Resolution-invariant Person ReID Based on Feature Transformation and Self-weighted Attention
Ziyue Zhang, Shuai Jiang, Congzhentao Huang +1
Person Re-identification (ReID) is a critical computer vision task which aims to match the same person in images or video sequences. Most current works focus on settings where the…
Bayesian data assimilation for estimating epidemic evolution: a COVID-19 study
Xian Yang, Shuo Wang, Yuting Xing +4
The evolution of epidemiological parameters, such as instantaneous reproduction number Rt, is important for understanding the transmission dynamics of infectious diseases. Current…
Implicit bias of deep linear networks in the large learning rate phase
Wei Huang, Weitao Du, Richard Yi Da Xu +1
Most theoretical studies explaining the regularization effect in deep learning have only focused on gradient descent with a sufficient small learning rate or even gradient flow (in…
RGB-IR Cross-modality Person ReID based on Teacher-Student GAN Model
Ziyue Zhang, Shuai Jiang, Congzhentao Huang +2
RGB-Infrared (RGB-IR) person re-identification (ReID) is a technology where the system can automatically identify the same person appearing at different parts of a video when light…
On the Neural Tangent Kernel of Deep Networks with Orthogonal Initialization
Wei Huang, Weitao Du, Richard Yi Da Xu
The prevailing thinking is that orthogonal weights are crucial to enforcing dynamical isometry and speeding up training. The increase in learning speed that results from orthogonal…
Time-varying neural network for stock return prediction
Steven Y. K. Wong, Jennifer Chan, Lamiae Azizi +1
We consider the problem of neural network training in a time-varying context. Machine learning algorithms have excelled in problems that do not change over time. However, problems…
Illumination adaptive person reid based on teacher-student model and adversarial training
Ziyue Zhang, Richard YD Xu, Shuai Jiang +3
Most existing works in Person Re-identification (ReID) focus on settings where illumination either is kept the same or has very little fluctuation. However, the changes in the illu…