English

Hypernetwork-Driven Model Fusion for Federated Domain Generalization

Machine Learning 2024-05-29 v3

Abstract

Federated Learning (FL) faces significant challenges with domain shifts in heterogeneous data, degrading performance. Traditional domain generalization aims to learn domain-invariant features, but the federated nature of model averaging often limits this due to its linear aggregation of local learning. To address this, we propose a robust framework, coined as hypernetwork-based Federated Fusion (hFedF), using hypernetworks for non-linear aggregation, facilitating generalization to unseen domains. Our method employs client-specific embeddings and gradient alignment techniques to manage domain generalization effectively. Evaluated in both zero-shot and few-shot settings, hFedF demonstrates superior performance in handling domain shifts. Comprehensive comparisons on PACS, Office-Home, and VLCS datasets show that hFedF consistently achieves the highest in-domain and out-of-domain accuracy with reliable predictions. Our study contributes significantly to the under-explored field of Federated Domain Generalization (FDG), setting a new benchmark for performance in this area.

Keywords

Cite

@article{arxiv.2402.06974,
  title  = {Hypernetwork-Driven Model Fusion for Federated Domain Generalization},
  author = {Marc Bartholet and Taehyeon Kim and Ami Beuret and Se-Young Yun and Joachim M. Buhmann},
  journal= {arXiv preprint arXiv:2402.06974},
  year   = {2024}
}
R2 v1 2026-06-28T14:44:57.201Z