Picture for Richard Yi Da Xu

Richard Yi Da Xu

TsCA: On the Semantic Consistency Alignment via Conditional Transport for Compositional Zero-Shot Learning

Add code
Aug 16, 2024
Viaarxiv icon

KERMIT: Knowledge Graph Completion of Enhanced Relation Modeling with Inverse Transformation

Add code
Sep 26, 2023
Viaarxiv icon

A variational autoencoder-based nonnegative matrix factorisation model for deep dictionary learning

Add code
Jan 18, 2023
Viaarxiv icon

Free Lunch for Generating Effective Outlier Supervision

Add code
Jan 17, 2023
Viaarxiv icon

Demystify Optimization and Generalization of Over-parameterized PAC-Bayesian Learning

Add code
Feb 04, 2022
Figure 1 for Demystify Optimization and Generalization of Over-parameterized PAC-Bayesian Learning
Figure 2 for Demystify Optimization and Generalization of Over-parameterized PAC-Bayesian Learning
Figure 3 for Demystify Optimization and Generalization of Over-parameterized PAC-Bayesian Learning
Viaarxiv icon

Regularize! Don't Mix: Multi-Agent Reinforcement Learning without Explicit Centralized Structures

Add code
Sep 19, 2021
Figure 1 for Regularize! Don't Mix: Multi-Agent Reinforcement Learning without Explicit Centralized Structures
Figure 2 for Regularize! Don't Mix: Multi-Agent Reinforcement Learning without Explicit Centralized Structures
Figure 3 for Regularize! Don't Mix: Multi-Agent Reinforcement Learning without Explicit Centralized Structures
Figure 4 for Regularize! Don't Mix: Multi-Agent Reinforcement Learning without Explicit Centralized Structures
Viaarxiv icon

Dual Behavior Regularized Reinforcement Learning

Add code
Sep 19, 2021
Figure 1 for Dual Behavior Regularized Reinforcement Learning
Figure 2 for Dual Behavior Regularized Reinforcement Learning
Figure 3 for Dual Behavior Regularized Reinforcement Learning
Figure 4 for Dual Behavior Regularized Reinforcement Learning
Viaarxiv icon

Greedy UnMixing for Q-Learning in Multi-Agent Reinforcement Learning

Add code
Sep 19, 2021
Figure 1 for Greedy UnMixing for Q-Learning in Multi-Agent Reinforcement Learning
Figure 2 for Greedy UnMixing for Q-Learning in Multi-Agent Reinforcement Learning
Figure 3 for Greedy UnMixing for Q-Learning in Multi-Agent Reinforcement Learning
Figure 4 for Greedy UnMixing for Q-Learning in Multi-Agent Reinforcement Learning
Viaarxiv icon

Alleviating Mode Collapse in GAN via Diversity Penalty Module

Add code
Aug 24, 2021
Figure 1 for Alleviating Mode Collapse in GAN via Diversity Penalty Module
Figure 2 for Alleviating Mode Collapse in GAN via Diversity Penalty Module
Figure 3 for Alleviating Mode Collapse in GAN via Diversity Penalty Module
Figure 4 for Alleviating Mode Collapse in GAN via Diversity Penalty Module
Viaarxiv icon

Wide Graph Neural Networks: Aggregation Provably Leads to Exponentially Trainability Loss

Add code
Mar 03, 2021
Figure 1 for Wide Graph Neural Networks: Aggregation Provably Leads to Exponentially Trainability Loss
Figure 2 for Wide Graph Neural Networks: Aggregation Provably Leads to Exponentially Trainability Loss
Figure 3 for Wide Graph Neural Networks: Aggregation Provably Leads to Exponentially Trainability Loss
Figure 4 for Wide Graph Neural Networks: Aggregation Provably Leads to Exponentially Trainability Loss
Viaarxiv icon