Decentralized Federated Dataset Dictionary Learning for Multi-Source Domain Adaptation
This work addresses domain adaptation for decentralized and privacy-sensitive applications, but it is incremental as it extends an existing federated framework.
The paper tackled decentralized multi-source domain adaptation by proposing a fully decentralized federated approach that eliminates the need for a central server, showing effective adaptation of source domains to an unlabeled target domain.
Decentralized Multi-Source Domain Adaptation (DMSDA) is a challenging task that aims to transfer knowledge from multiple related and heterogeneous source domains to an unlabeled target domain within a decentralized framework. Our work tackles DMSDA through a fully decentralized federated approach. In particular, we extend the Federated Dataset Dictionary Learning (FedDaDiL) framework by eliminating the necessity for a central server. FedDaDiL leverages Wasserstein barycenters to model the distributional shift across multiple clients, enabling effective adaptation while preserving data privacy. By decentralizing this framework, we enhance its robustness, scalability, and privacy, removing the risk of a single point of failure. We compare our method to its federated counterpart and other benchmark algorithms, showing that our approach effectively adapts source domains to an unlabeled target domain in a fully decentralized manner.