From Classifier Heads to Encoder Prototypes: Personalized Federated Learning with Head-Derived Clustering

Paper recorded by Signals 4 on 2026-10-21 in cs.LG. Abstract reproduced from arXiv; link to the original below.

Published 2026-10-21 on arXiv · recorded by Signals 4 on 2026-10-22

Category: cs.LG · 机器学习 · first seen 2026-10-22

Abstract

Personalized federated learning must decide which clients should share representations. We introduce HDC-FL (Head-Derived Clustering for Personalized Federated Learning), which reads that decision off a signal shared-encoder training already produces: the client-specific classifi- er heads. At periodic refresh rounds the server projects the cached heads into a normalized low-rank descriptor space,

Read on arXiv →