DeFed-GMM-DaDiL: A Decentralized Federated Framework for Domain Adaptation

2026-05-05

Abstract

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.

Problem

• decentralized
• multi-source domain adaptation
• federated learning
• missing classes
• domain adaptation

Innovation

• Decentralized Federated Learning
• Gaussian Mixture Model
• Wasserstein Barycenter
• Domain Adaptation
• Privacy-Preserving