Unsupervised domain adaptation with a relaxed covariate shift assumption

Tameem Adel, Han Zhao, Alexander Wong

Research output: Contribution to conferencePaperpeer-review


Domain adaptation addresses learning tasks where training is performed on data from one domain whereas testing is performed on data belonging to a different but related domain. Assumptions about the relationship between the source and target domains should lead to tractable solutions on the one hand, and be realistic on the other hand. Here we propose a generative domain adaptation model that allows for modelling different assumptions about this relationship, among which is a newly introduced assumption that replaces covariate shift with a possibly more realistic assumption without losing tractability due to the efficient variational inference procedure developed. In addition to the ability to model less restrictive relationships between source and target, modelling can be performed without any target labeled data (unsupervised domain adaptation). We also provide a Rademacher complexity bound of the proposed algorithm. We evaluate the model on the Amazon reviews and the CVC pedestrian detection datasets.

Original languageEnglish (US)
Number of pages7
StatePublished - 2017
Externally publishedYes
Event31st AAAI Conference on Artificial Intelligence, AAAI 2017 - San Francisco, United States
Duration: Feb 4 2017Feb 10 2017


Other31st AAAI Conference on Artificial Intelligence, AAAI 2017
Country/TerritoryUnited States
CitySan Francisco

ASJC Scopus subject areas

  • Artificial Intelligence


Dive into the research topics of 'Unsupervised domain adaptation with a relaxed covariate shift assumption'. Together they form a unique fingerprint.

Cite this