Efficiently Assemble Normalization Layers and Regularization for Federated Domain Generalization

TL;DR

This paper introduces gPerXAN, a novel federated learning approach that combines specialized normalization and regularization techniques to improve model generalization across unseen domains while preserving privacy and reducing communication costs.

Contribution

The paper proposes a new architectural method, gPerXAN, for federated domain generalization that uses personalized normalization and a guiding regularizer to enhance domain-invariant feature learning.

Findings

Outperforms existing methods on PACS, Office-Home, and Camelyon17 datasets.

Effectively filters domain-specific features while capturing invariant representations.

Reduces privacy risks and communication costs in federated learning.

Abstract

Domain shift is a formidable issue in Machine Learning that causes a model to suffer from performance degradation when tested on unseen domains. Federated Domain Generalization (FedDG) attempts to train a global model using collaborative clients in a privacy-preserving manner that can generalize well to unseen clients possibly with domain shift. However, most existing FedDG methods either cause additional privacy risks of data leakage or induce significant costs in client communication and computation, which are major concerns in the Federated Learning paradigm. To circumvent these challenges, here we introduce a novel architectural method for FedDG, namely gPerXAN, which relies on a normalization scheme working with a guiding regularizer. In particular, we carefully design Personalized eXplicitly Assembled Normalization to enforce client models selectively filtering domain-specific features that are biased towards local data while retaining discrimination of those features. Then, we incorporate a simple yet effective regularizer to guide these models in directly capturing domain-invariant representations that the global model's classifier can leverage. Extensive experimental results on two benchmark datasets, i.e., PACS and Office-Home, and a real-world medical dataset, Camelyon17, indicate that our proposed method outperforms other existing methods in addressing this particular problem.