.png){kind=icon}
返回
FRuDA: Framework for Distributed Adversarial Domain Adaptation
.png){kind=icon}
OA
AI
DOI：10.1109/TPDS.2021.3136673.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
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 fora 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 x.
Keyword:
Distributed domain adaptation
domain shift
adversarial learning
期刊
IF:
6
论文数:
5.2K
被引数:
1.1W
机构
引用论文
Structural characterization of [Crypt221-Na] 2 [H2Ru4 (CO) 12][Crypt222-K] 2 [Ru4 (CO) 13].png)
Polyhedron
PolyhedronIF0
PREAI
分享收藏Effect of Chemical Treatments on the Physical Properties of Non-woven Jute/PLA Biocomposites化学处理对非织造黄麻/PLA生物复合材料物理性能的影响BioResources
OAAI
BioResourcesIF0
OAAI分享收藏
查看更多内容