FRuDA: Framework for Distributed Adversarial Domain Adaptation

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