FRuDA: Framework for Distributed Adversarial Domain Adaptation
It addresses a gap in applying adversarial uDA to real-world distributed scenarios, such as on thousands of devices, which is incremental as it extends existing methods to new settings.
The paper tackles the problem of adapting unsupervised domain adaptation (uDA) algorithms, particularly adversarial ones, to distributed settings where target domains are spread across many devices, and introduces FRuDA, a framework that boosts target domain accuracy by up to 50% and improves training efficiency by at least 11 times.
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.