Federated Dataset Dictionary Learning for Multi-Source Domain Adaptation

TL;DR

This paper introduces FedDaDiL, a federated domain adaptation method using dictionary learning of empirical distributions, enabling privacy-preserving adaptation across multiple client domains with unlabeled data.

Contribution

It presents a novel federated framework for domain adaptation that preserves privacy through collaborative dictionary learning of empirical distributions.

Findings

Successfully generates labeled data in target domains

Outperforms centralized and other federated methods

Effective on multiple benchmark datasets

Abstract

In this article, we propose an approach for federated domain adaptation, a setting where distributional shift exists among clients and some have unlabeled data. The proposed framework, FedDaDiL, tackles the resulting challenge through dictionary learning of empirical distributions. In our setting, clients' distributions represent particular domains, and FedDaDiL collectively trains a federated dictionary of empirical distributions. In particular, we build upon the Dataset Dictionary Learning framework by designing collaborative communication protocols and aggregation operations. The chosen protocols keep clients' data private, thus enhancing overall privacy compared to its centralized counterpart. We empirically demonstrate that our approach successfully generates labeled data on the target domain with extensive experiments on (i) Caltech-Office, (ii) TEP, and (iii) CWRU benchmarks. Furthermore, we compare our method to its centralized counterpart and other benchmarks in federated domain adaptation.