Domain-Skewed Federated Learning with Feature Decoupling and Calibration

TL;DR

This paper introduces F^2DC, a federated learning method that addresses domain skew by decoupling and calibrating features, leading to more robust and generalizable models across diverse domains.

Contribution

The paper proposes a novel federated learning framework with domain feature decoupling and calibration, improving model robustness in multi-domain settings.

Findings

F^2DC outperforms baseline methods on multi-domain datasets.

The Domain Feature Decoupler effectively separates domain-robust and domain-related features.

Calibration of domain-related features enhances model generalization.

Abstract

Federated learning (FL) allows distributed clients to collaboratively train a global model in a privacy-preserving manner. However, one major challenge is domain skew, where clients' data originating from diverse domains may hinder the aggregated global model from learning a consistent representation space, resulting in poor generalizable ability in multiple domains. In this paper, we argue that the domain skew is reflected in the domain-specific biased features of each client, causing the local model's representations to collapse into a narrow low-dimensional subspace. We then propose Federated Feature Decoupling and Calibration ($F^2$DC), which liberates valuable class-relevant information by calibrating the domain-specific biased features, enabling more consistent representations across domains. A novel component, Domain Feature Decoupler (DFD), is first introduced in $F^2$DC to determine the robustness of each feature unit, thereby separating the local features into domain-robust features and domain-related features. A Domain Feature Corrector (DFC) is further proposed to calibrate these domain-related features by explicitly linking discriminative signals, capturing additional class-relevant clues that complement the domain-robust features. Finally, a domain-aware aggregation of the local models is performed to promote consensus among clients. Empirical results on three popular multi-domain datasets demonstrate the effectiveness of the proposed $F^2$DC and the contributions of its two modules. Code is available at https://github.com/mala-lab/F2DC.