Abstract
Unsupervised domain adaptation (UDA) is a popular machine learning technique that allows one to train models over diverse data collected from different domains. However, this technique requires the learner to collect a large number of properly labeled data samples, which can be costly and unrealistic in many applications. In this work, we propose a decentralized assisted learning framework for UDA. In this framework, a learner has only a limited number of labeled data samples collected from a certain source domain and aims to train a classifier for the target domain. To improve domain adaptation performance, it seeks assistance by interacting with an external service provider, who possesses many labeled data samples collected from a related source domain. We develop an assisted UDA algorithm that avoids data sharing and can significantly improve the learner's domain adaptation performance within a few rounds of interaction. Experiments using deep neural networks on benchmark datasets demonstrate the effectiveness of this algorithm.
Original language | English |
---|---|
Title of host publication | 2023 IEEE International Symposium on Information Theory, ISIT 2023 |
Pages | 2482-2487 |
Number of pages | 6 |
ISBN (Electronic) | 9781665475549 |
DOIs | |
State | Published - 2023 |
Event | 2023 IEEE International Symposium on Information Theory, ISIT 2023 - Taipei, Taiwan, Province of China Duration: Jun 25 2023 → Jun 30 2023 |
Publication series
Name | IEEE International Symposium on Information Theory - Proceedings |
---|---|
Volume | 2023-June |
ISSN (Print) | 2157-8095 |
Conference
Conference | 2023 IEEE International Symposium on Information Theory, ISIT 2023 |
---|---|
Country/Territory | Taiwan, Province of China |
City | Taipei |
Period | 6/25/23 → 6/30/23 |
Bibliographical note
Publisher Copyright:© 2023 IEEE.
Funding
ACKNOWLEDGMENTS This paper is based upon work supported by the Army Research Laboratory and the Army Research Office under grant number W911NF-20-1-0222 and National Science Foundation under grant number DMS-2134148. The work of Cheng Chen and Yi Zhou was supported in part by U.S. National Science Foundation under the Grant. Nos. CCF-2106216, DMS-2134223 and CAREER-2237830.
Funders | Funder number |
---|---|
National Science Foundation (NSF) | DMS-2134148 |
Army Research Office | W911NF-20-1-0222 |
Army Research Laboratory |
ASJC Scopus subject areas
- Theoretical Computer Science
- Information Systems
- Modeling and Simulation
- Applied Mathematics