Timezone: »

 
Poster
Continuously Indexed Domain Adaptation
Hao Wang · Hao He · Dina Katabi

Tue Jul 14 02:00 PM -- 02:45 PM & Wed Jul 15 03:00 AM -- 03:45 AM (PDT) @
in Poster Session 8 »

Existing domain adaptation focuses on transferring knowledge between domains with categorical indices (e.g., between datasets A and B). However, many tasks involve continuously indexed domains. For example, in medical applications, one often needs to transfer disease analysis and prediction across patients of different ages, where age acts as a continuous domain index. Such tasks are challenging for prior domain adaptation methods since they ignore the underlying relation among domains. In this paper, we propose the first method for continuously indexed domain adaptation. Our approach combines traditional adversarial adaptation with a novel discriminator that models the encoding-conditioned domain index distribution. Our theoretical analysis demonstrates the value of leveraging the domain index to generate invariant features across a continuous range of domains. Our empirical results show that our approach outperforms the state-of-the-art domain adaption methods on both synthetic and real-world medical datasets.

Keywords: Generative Adversarial Networks · Healthcare · Transfer and Multitask Learning · Social Good Applications · Applications - Neuroscience, Cognitive Science, Biology and Health

Author Information

Hao Wang (MIT)
Hao He (Massachusetts Institute of Technology)
Dina Katabi (MIT)

More from the Same Authors