AISTATS 2021poster31 citations

A Theory of Multiple-Source Adaptation with Limited Target Labeled Data

Yishay Mansour, Mehryar Mohri, Jae Ro, Ananda Theertha Suresh, Ke Wu

Abstract

We study multiple-source domain adaptation, when the learner has access to abundant labeled data from multiple-source domains and limited labeled data from the target domain. We analyze existing algorithms for this problem, and propose a novel algorithm based on model selection. Our algorithms are efficient, and experiments on real data-sets empirically demonstrate their benefits.

BibTeX
@InProceedings{pmlr-v130-mansour21a,
  title = 	 { A Theory of Multiple-Source Adaptation with Limited Target Labeled Data },
  author =       {Mansour, Yishay and Mohri, Mehryar and Ro, Jae and Theertha Suresh, Ananda and Wu, Ke},
  booktitle = 	 {Proceedings of The 24th International Conference on Artificial Intelligence and Statistics},
  pages = 	 {2332--2340},
  year = 	 {2021},
  editor = 	 {Banerjee, Arindam and Fukumizu, Kenji},
  volume = 	 {130},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {13--15 Apr},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v130/mansour21a/mansour21a.pdf},
  url = 	 {https://proceedings.mlr.press/v130/mansour21a.html},
  abstract = 	 { We study multiple-source domain adaptation, when the learner has access to abundant labeled data from multiple-source domains and limited labeled data from the target domain. We analyze existing algorithms for this problem, and propose a novel algorithm based on model selection. Our algorithms are efficient, and experiments on real data-sets empirically demonstrate their benefits. }
}
A Theory of Multiple-Source Adaptation with Limited Target Labeled Data · AISTATS 2021