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

arXiv: https://arxiv.org/abs/2605.04324 · HTML: https://mlsanity.com/paper/2605.04324/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 24 references that are in the map.
- First posted on arXiv 5 May 2026.

## Builds on (most cited first, 15 of 15)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [Deep Hashing Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1706.07522/) (2017)
- [Federated Adversarial Domain Adaptation](https://mlsanity.com/paper/1911.02054/) (2019)
- [A Wasserstein-type distance in the space of Gaussian Mixture Models](https://mlsanity.com/paper/1907.05254/) (2019)
- [Recent Advances in Optimal Transport for Machine Learning](https://mlsanity.com/paper/2306.16156/) (2023)
- [KD3A: Unsupervised Multi-Source Decentralized Domain Adaptation via Knowledge Distillation](https://mlsanity.com/paper/2011.09757/) (2020)
- [Multi-source Domain Adaptation via Weighted Joint Distributions Optimal Transport](https://mlsanity.com/paper/2006.12938/) (2020)
- [Towards Novel Target Discovery Through Open-Set Domain Adaptation](https://mlsanity.com/paper/2105.02432/) (2021)
- [Multi-Source Domain Adaptation through Dataset Dictionary Learning in Wasserstein Space](https://mlsanity.com/paper/2307.14953/) (2023)
- [Missing-Class-Robust Domain Adaptation by Unilateral Alignment for Fault Diagnosis](https://mlsanity.com/paper/2001.02015/) (2020)
- [Lighter, Better, Faster Multi-Source Domain Adaptation with Gaussian Mixture Models and Optimal Transport](https://mlsanity.com/paper/2404.10261/) (2024)
- [Federated Dataset Dictionary Learning for Multi-Source Domain Adaptation](https://mlsanity.com/paper/2309.07670/) (2023)
- [Decentralized Federated Dataset Dictionary Learning for Multi-Source Domain Adaptation](https://mlsanity.com/paper/2503.17683/) (2025)

## Abstract (arXiv)

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.