3 papers
cs.LG2026
Does the Trust Boundary Hold over Time? A Long-Horizon Benchmark for Receiver-Directed Federated Learning
Ting Xu, Henry Leung
In receiver-directed federated learning, each site draws a trust boundary. For every source and model component it judges, on its own data, whether the transfer helps (admit), harm…
cs.AI2026
Fed-Universe: A Semantic-Geometric-Topological-Human (S-G-T-H) Stack for Negotiated Alignment in Federated Systems
Ting Xu, Henry Leung
Conventional federated learners implicitly optimize for global means, creating a "one-size-fits-all" paradigm that inevitably suppresses the minority under cross-site heterogeneity…
cs.LG2026
Fed-Equilibrium Framework for Topological Pareto Control in Robust and Fair Clinical Federated Learning
Ting Xu, Henry Leung
The deployment of Federated Learning (FL) in multi-center clinical networks faces the challenge of "knowledge dominance," where high-volume hubs naturally overwhelm minority commun…