Federated Multi-Target Domain Adaptation

Abstract

Federated learning methods enable us to train machine learning models on distributed user data while preserving its privacy. However, it is not always feasible to obtain high-quality supervisory signals from users, especially for vision tasks. Unlike typical federated settings with labeled client data, we consider a more practical scenario where the distributed client data is unlabeled, and a centralized labeled dataset is available on the server. We further take the server-client and inter-client domain shifts into account and pose a domain adaptation problem with one source (centralized server data) and multiple targets (distributed client data). Within this new Federated Multi-Target Domain Adaptation (FMTDA) task, we analyze the model performance of exiting domain adaptation methods and propose an effective DualAdapt method to address the new challenges. Extensive experimental results on image classification and semantic segmentation tasks demonstrate that our method achieves high accuracy, incurs minimal communication cost, and requires low computational resources on client devices.

Algorithm Fairness in AI for Medicine and Healthcare

“…Many of the current research directions in federated learning point towards multi-site domain adaptation across distributed clients [191][192][193][194][195] . For instance, Federated Multi-Target Domain Adaptation (FMTDA) is a task that addresses domain gaps between unlabeled, distributed client data and labeled, centralized data over the server, as well as degraded performances of federated domain adaptation methods 196 .…”