AI RESEARCH
A Taxonomy and Resolution Strategy for Client-Level Disagreements in Federated Learning
arXiv CS.LG
•
ArXi:2604.23386v1 Announce Type: cross Federated Learning (FL) typically assumes unconditional collaboration, a premise that overlooks the complexities of real-world, multi-stakeholder environments in which clients may need to exclude one another for strategic, regulatory, or competitive reasons. This paper addresses this gap, which we term 'client-level disagreements,' by first