SOURCE-LINKED INTELLIGENCE

FedFIbOS: Fisher Importance based Optimal Submodelling for Heterogeneous Federated Learning

arXiv · AI, language, vision and robotics · article · Sep 17, 2026 · UTC

Heterogeneous federated learning requires clients with diverse computational capacities to collaboratively train a global model, where each client trains a capacity-constrained submodel. Existing methods select submodel parameters using heuristic importance measures---most prominently parameter magnitude---without theoretical justification for why these measures support convergence. We identify a fundamental gap: existing parameter selection criteria lack theoretical grounding in the convergence framework, partial client participation introduces additional estimation effects in the Fisher scor

Read original source ↗ Open in workspace

recordType

paper

region

Global