Multi-Source Collaborative Gradient Discrepancy Minimization for Federated Domain Generalization

TL;DR

This paper introduces a novel federated domain generalization method that minimizes gradient discrepancies within and across source domains, improving model generalization to unseen target domains while preserving data privacy.

Contribution

The proposed MCGDM method uniquely combines intra- and inter-domain gradient matching to enhance federated domain generalization and can be extended to domain adaptation tasks.

Findings

Outperforms state-of-the-art methods on federated domain generalization benchmarks.

Effectively reduces domain shift through collaborative gradient discrepancy minimization.

Extends to domain adaptation with fine-tuning on pseudo-labeled target data.

Abstract

Federated Domain Generalization aims to learn a domain-invariant model from multiple decentralized source domains for deployment on unseen target domain. Due to privacy concerns, the data from different source domains are kept isolated, which poses challenges in bridging the domain gap. To address this issue, we propose a Multi-source Collaborative Gradient Discrepancy Minimization (MCGDM) method for federated domain generalization. Specifically, we propose intra-domain gradient matching between the original images and augmented images to avoid overfitting the domain-specific information within isolated domains. Additionally, we propose inter-domain gradient matching with the collaboration of other domains, which can further reduce the domain shift across decentralized domains. Combining intra-domain and inter-domain gradient matching, our method enables the learned model to generalize well on unseen domains. Furthermore, our method can be extended to the federated domain adaptation task by fine-tuning the target model on the pseudo-labeled target domain. The extensive experiments on federated domain generalization and adaptation indicate that our method outperforms the state-of-the-art methods significantly.