FRuDA: Framework for Distributed Adversarial Domain Adaptation

• Published in: IEEE transactions on parallel and distributed systems 2022-11, Vol.33 (11), p.3153-3164
• Main Authors: Gan, Shaoduo, Mathur, Akhil, Isopoussu, Anton, Kawsar, Fahim, Berthouze, Nadia, Lane, Nicholas D.
• Format: Article
• Language: English
• Subjects: Accuracy; Adaptation; Adaptation models; adversarial learning; Algorithms; Classification algorithms; Costs; Data models; Distributed domain adaptation; domain shift; Domains; Electronics packaging; Feature extraction; Machine learning; Training
• ISSN: 1045-9219; 1558-2183
• DOI: 10.1109/TPDS.2021.3136673

Breakthroughs in unsupervised domain adaptation (uDA) can help in adapting models from a label-rich source domain to unlabeled target domains. Despite these advancements, there is a lack of research on how uDA algorithms, particularly those based on adversarial learning, can work in distributed settings. In real-world applications, target domains are often distributed across thousands of devices, and existing adversarial uDA algorithms - which are centralized in nature - cannot be applied in these settings. To solve this important problem, we introduce FRuDA: an end-to-end framework for distributed adversarial uDA. Through a careful analysis of the uDA literature, we identify the design goals for a distributed uDA system and propose two novel algorithms to increase adaptation accuracy and training efficiency of adversarial uDA in distributed settings. Our evaluation of FRuDA with five image and speech datasets show that it can boost target domain accuracy by up to 50% and improve the training efficiency of adversarial uDA by at least 11\times 11× .