SOURCE-LINKED INTELLIGENCE

Joint Domain-Class Modeling for Federated Learning Under Feature Skew

arXiv · AI, language, vision and robotics · article · Sep 19, 2026 · UTC

Federated learning (FL) enables collaborative model training without centralizing private data, but performance often degrades under feature skew: clients share labels while the conditional input distributions $p_i(x\!\mid\!y)$ vary due to latent, client-specific appearance factors. We propose Joint Domain-Class Federated Learning (JDFL), a lightweight, optimizer-agnostic extension that makes this latent domain variation usable without sharing raw data. JDFL first infers domain clusters called pseudo-domains from brief local update signals. It then expands the classifier head to output $M\time

Read original source ↗ Open in workspace

recordType

paper

region

Global