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

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

Research output: Contribution to journalConference articlepeer-review

Abstract

We present a theoretical and algorithmic study of the multiple-source domain adaptation problem in the common scenario where the learner has access only to a limited amount of labeled target data, but where the learner has at their disposal a large amount of labeled data from multiple source domains. We show that a new family of algorithms based on model selection ideas benefits from very favorable guarantees in this scenario and discuss some theoretical obstacles affecting some alternative techniques. We also report the results of several experiments with our algorithms that demonstrate their practical effectiveness.

Original languageEnglish (US)
Pages (from-to)2332-2340
Number of pages9
JournalProceedings of Machine Learning Research
Volume130
StatePublished - 2021
Event24th International Conference on Artificial Intelligence and Statistics, AISTATS 2021 - Virtual, Online, United States
Duration: Apr 13 2021Apr 15 2021

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software
  • Control and Systems Engineering
  • Statistics and Probability

Fingerprint

Dive into the research topics of 'A Theory of Multiple-Source Adaptation with Limited Target Labeled Data'. Together they form a unique fingerprint.

Cite this