Han Yu

7 papers Nanyang Technological University (NTU)

• A Reinforcement Learning-based Bidding Strategy for Data Consumers in Auction-based Federated Learning
• Class-wise Balancing Data Replay for Federated Class-Incremental Learning
• Class-wise Balancing Data Replay for Federated Class-Incremental Learning
• CrossSpectra: Exploiting Cross-Layer Smoothness for Parameter-Efficient Fine-Tuning
• Global Prompt Refinement with Non-Interfering Attention Masking for One-Shot Federated Learning
• Personalized Subgraph Federated Learning with Differentiable Auxiliary Projections
• Tight High-Probability Bounds for Nonconvex Heavy-Tailed Scenario under Weaker Assumptions