Generative Gradual Domain Adaptation with Optimal Transport

Yifei He, Haoxiang Wang, Han Zhao

Keywords: Domain Adaptation, Gradual Domain Adaptation, Distribution Shift

Abstract: Unsupervised domain adaptation (UDA) adapts a model from a labeled source domain to an unlabeled target domain in a one-off way. Though widely applied, UDA faces a great challenge whenever the distribution shift between the source and the target is large. Gradual domain adaptation (GDA) mitigates this limitation by using intermediate domains to gradually adapt from the source to the target domain. However, it remains an open problem on how to leverage this paradigm when the oracle intermediate domains are missing or scarce. To approach this practical challenge, we propose Generative Gradual Domain Adaptation with Optimal Transport (GOAT), an algorithmic framework that can generate intermediate domains in a data-dependent way. More concretely, we generate intermediate domains along the Wasserstein geodesic between two given consecutive domains in a feature space, and apply gradual self-training, a standard GDA algorithm, to adapt the source-trained classifier to the target along the sequence of intermediate domains. Empirically, we demonstrate that our GOAT framework can improve the performance of standard GDA when the oracle intermediate domains are scarce, significantly broadening the real-world application scenarios of GDA.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: General Machine Learning (ie none of the above)