Timezone: »

 
Poster
Label-Noise Robust Domain Adaptation
Xiyu Yu · Tongliang Liu · Mingming Gong · Kun Zhang · Kayhan Batmanghelich · Dacheng Tao

Wed Jul 15 05:00 AM -- 05:45 AM & Wed Jul 15 07:00 PM -- 07:45 PM (PDT) @ None #None
in Poster Session 21 »
Domain adaptation aims to correct the classifiers when faced with distribution shift between source (training) and target (test) domains. State-of-the-art domain adaptation methods make use of deep networks to extract domain-invariant representations. However, existing methods assume that all the instances in the source domain are correctly labeled; while in reality, it is unsurprising that we may obtain a source domain with noisy labels. In this paper, we are the first to comprehensively investigate how label noise could adversely affect existing domain adaptation methods in various scenarios. Further, we theoretically prove that there exists a method that can essentially reduce the side-effect of noisy source labels in domain adaptation. Specifically, focusing on the generalized target shift scenario, where both label distribution $P_Y$ and the class-conditional distribution $P_{X|Y}$ can change, we discover that the denoising Conditional Invariant Component (DCIC) framework can provably ensures (1) extracting invariant representations given examples with noisy labels in the source domain and unlabeled examples in the target domain and (2) estimating the label distribution in the target domain with no bias. Experimental results on both synthetic and real-world data verify the effectiveness of the proposed method.
Keywords: Transfer and Multitask Learning · Unsupervised and Semi-supervised Learning · Semi-supervised Learning · Unsupervised and Semi-Supervised Learning

Author Information

Xiyu Yu (Baidu Inc.)
Tongliang Liu (The University of Sydney)
Mingming Gong (University of Melbourne)
Kun Zhang (Carnegie Mellon University)
Kayhan Batmanghelich (University of Pittsburgh)
Dacheng Tao (The University of Sydney)

More from the Same Authors