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

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

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 journal › Conference article › peer-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 language	English
Pages (from-to)	2332-2340
Number of pages	9
Journal	Proceedings of Machine Learning Research
Volume	130
State	Published - 2021
Externally published	Yes
Event	24th International Conference on Artificial Intelligence and Statistics, AISTATS 2021 - Virtual, Online, United States Duration: 13 Apr 2021 → 15 Apr 2021

All Science Journal Classification (ASJC) codes

Artificial Intelligence
Software
Control and Systems Engineering
Statistics and Probability

Cite this

@article{7708a4d6627147a7af9b44502cf0fc4b,

title = "A Theory of Multiple-Source Adaptation with Limited Target Labeled Data",

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.",

author = "Yishay Mansour and Mehryar Mohri and Jae Ro and Suresh, {Ananda Theertha} and Ke Wu",

note = "Publisher Copyright: Copyright {\textcopyright} 2021 by the author(s); 24th International Conference on Artificial Intelligence and Statistics, AISTATS 2021 ; Conference date: 13-04-2021 Through 15-04-2021",

year = "2021",

language = "الإنجليزيّة",

volume = "130",

pages = "2332--2340",

journal = "Proceedings of Machine Learning Research",

issn = "2640-3498",

}

TY - JOUR

T1 - A Theory of Multiple-Source Adaptation with Limited Target Labeled Data

AU - Mansour, Yishay

AU - Mohri, Mehryar

AU - Ro, Jae

AU - Suresh, Ananda Theertha

AU - Wu, Ke

PY - 2021

Y1 - 2021

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85161801097&partnerID=8YFLogxK

M3 - مقالة من مؤنمر

SN - 2640-3498

VL - 130

SP - 2332

EP - 2340

JO - Proceedings of Machine Learning Research

JF - Proceedings of Machine Learning Research

T2 - 24th International Conference on Artificial Intelligence and Statistics, AISTATS 2021

Y2 - 13 April 2021 through 15 April 2021

ER -

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

Abstract

All Science Journal Classification (ASJC) codes

Other files and links

Fingerprint

Cite this