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

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.

Cite

Text

Mansour et al. "A Theory of Multiple-Source Adaptation with Limited Target Labeled Data." Artificial Intelligence and Statistics, 2021.

Markdown

[Mansour et al. "A Theory of Multiple-Source Adaptation with Limited Target Labeled Data." Artificial Intelligence and Statistics, 2021.](https://mlanthology.org/aistats/2021/mansour2021aistats-theory/)

BibTeX

@inproceedings{mansour2021aistats-theory,
  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 = {Artificial Intelligence and Statistics},
  year      = {2021},
  pages     = {2332-2340},
  volume    = {130},
  url       = {https://mlanthology.org/aistats/2021/mansour2021aistats-theory/}
}