Federated Domain Generalization with Latent Space Inversion

TL;DR

This paper introduces a federated domain generalization method that uses latent space inversion for privacy-preserving local training and an importance-weighted aggregation to better handle non-i.i.d. data, achieving superior results with less communication.

Contribution

It proposes a novel latent space inversion technique for privacy-preserving local training and an importance-weighted aggregation strategy for improved federated domain generalization.

Findings

Outperforms state-of-the-art methods in federated domain generalization.

Reduces communication overhead compared to existing approaches.

Enhances privacy by using latent space inversion during local training.

Abstract

Federated domain generalization (FedDG) addresses distribution shifts among clients in a federated learning framework. FedDG methods aggregate the parameters of locally trained client models to form a global model that generalizes to unseen clients while preserving data privacy. While improving the generalization capability of the global model, many existing approaches in FedDG jeopardize privacy by sharing statistics of client data between themselves. Our solution addresses this problem by contributing new ways to perform local client training and model aggregation. To improve local client training, we enforce (domain) invariance across local models with the help of a novel technique, \textbf{latent space inversion}, which enables better client privacy. When clients are not \emph{i.i.d}, aggregating their local models may discard certain local adaptations. To overcome this, we propose an \textbf{important weight} aggregation strategy to prioritize parameters that significantly influence predictions of local models during aggregation. Our extensive experiments show that our approach achieves superior results over state-of-the-art methods with less communication overhead.