What to Do When the Access to the Source Data Is Constrained?

Abstract

A large majority of existing domain adaptation methods makes an assumption of freely available labeled source and unlabeled target data. They exploit the discrepancy between their distributions and build representations common to both target and source domains. In reality, such a simplifying assumption rarely holds, since source data are routinely a subject of legal and contractual constraints between data owners and data customers. Despite a limited access to source domain data, decision-making procedures might be available in the form of, e.g., classification rules trained on the source and made ready for a direct deployment and later reuse. In other cases, the owner of a source data is allowed to share a few representative examples such as class means. The aim of this chapter is therefore to address the domain adaptation problem in such constrained real world applications, i.e. where the reuse of source domain data is limited to classification rules or a few representative examples. As a solution, we extend recent techniques based on feature corruption and their marginalization, both considering supervised and unsupervised domain adaptation settings. The proposed models are tested and compared on private and publicly available source datasets showing significant performance gains despite the absence of the whole source data and shortage of labeled target data.