DeFed-GMM-DaDiL: A Decentralized Federated Framework for Domain Adaptation
This work addresses the problem of domain adaptation in decentralized settings with privacy constraints, offering a fully federated solution that handles missing classes.
DeFed-GMM-DaDiL enables decentralized multi-source domain adaptation without a central server by modeling datasets as GMMs and learning shared Wasserstein barycenters, achieving stable representations and competitive performance on benchmarks.
Decentralized multi-source domain adaptation seeks to transfer knowledge from multiple heterogeneous and related source domains to an unlabeled target domain in a decentralized setting. We address this challenge through a fully decentralized federated approach, DeFed-GMM-DaDiL, an extension of the GMM-Dataset Dictionary Learning (DaDiL) framework. Each client models its dataset as a Gaussian Mixture Model (GMM), and the federation jointly approximates them via labeled Wasserstein barycenters of shared, learnable GMM atoms. This design enables adaptation without a central server while preserving clients' privacy. We empirically study the stability of the learned representations in scenarios where the target domain has missing classes. Empirical results demonstrate that DeFed-GMM-DaDiL maintains stable and consistent shared representations across clients, effectively reconstructs missing classes, and achieves competitive performance on multi-source domain adaptation benchmarks.