FedSDAF: Leveraging Source Domain Awareness for Enhanced Federated Domain Generalization

TL;DR

FedSDAF introduces a novel federated domain generalization framework that leverages source domain-aware features through a dual-adapter architecture and bidirectional knowledge distillation, significantly improving performance on benchmark datasets.

Contribution

The paper proposes FedSDAF, a systematic approach that utilizes source domain knowledge via a dual-adapter architecture and bidirectional distillation to enhance federated domain generalization.

Findings

FedSDAF outperforms existing FedDG methods on benchmark datasets.

Source domain-aware features have superior generalization capabilities.

The dual-adapter architecture effectively separates local expertise from global consensus.

Abstract

Traditional Federated Domain Generalization (FedDG) methods focus on learning domain-invariant features or adapting to unseen target domains, often overlooking the unique knowledge embedded within the source domain, especially in strictly isolated federated learning environments. Through experimentation, we discovered a counterintuitive phenomenon: features learned from a complete source domain have superior generalization capabilities compared to those learned directly from the target domain. This insight leads us to propose the Federated Source Domain Awareness Framework (FedSDAF), the first systematic approach to enhance FedDG by leveraging source domain-aware features. FedSDAF employs a dual-adapter architecture that decouples "local expertise" from "global generalization consensus." A Domain-Aware Adapter, retained locally, extracts and protects the unique discriminative knowledge of each source domain, while a Domain-Invariant Adapter, shared across clients, builds a robust global consensus. To enable knowledge exchange, we introduce a Bidirectional Knowledge Distillation mechanism that facilitates efficient dialogue between the adapters. Extensive experiments on four benchmark datasets (OfficeHome, PACS, VLCS, and DomainNet) show that FedSDAF significantly outperforms existing FedDG methods. The source code is available at https://github.com/pizzareapers/FedSDAF.