TOHAN: A One-step Approach towards Few-shot Hypothesis Adaptation

Haoang Chi, Feng Liu, Wenjing Yang*, Long Lan*, Tongliang Liu, Bo Han, William Kwok Wai Cheung, James T. Kwok

*Corresponding author for this work

Research output: Chapter in book/report/conference proceedingConference contributionpeer-review

Abstract

In few-shot domain adaptation (FDA), classifiers for the target domain are trained with accessible labeled data in the source domain (SD) and few labeled data in the target domain (TD). However, data usually contain private information in the current era, e.g., data distributed on personal phones. Thus, the private data will be leaked if we directly access data in SD to train a target-domain classifier (required by FDA methods). In this paper, to prevent privacy leakage in SD, we consider a very challenging problem setting, where the classifier for the TD has to be trained using few labeled target data and a well-trained SD classifier, named few-shot hypothesis adaptation (FHA). In FHA, we cannot access data in SD, as a result, the private information in SD will be protected well. To this end, we propose a targetoriented hypothesis adaptation network (TOHAN) to solve the FHA problem, where we generate highly-compatible unlabeled data (i.e., an intermediate domain) to help train a target-domain classifier. TOHAN maintains two deep networks simultaneously, in which one focuses on learning an intermediate domain and the other takes care of the intermediate-to-target distributional adaptation and the target-risk minimization. Experimental results show that TOHAN outperforms competitive baselines significantly.

Original languageEnglish
Title of host publication35th Conference on Neural Information Processing Systems (NeurIPS 2021)
EditorsMarc'Aurelio Ranzato, Alina Beygelzimer, Yann Dauphin, Percy S. Liang, Jenn Wortman Vaughan
PublisherNeural Information Processing Systems Foundation
Pages20970-20982
Number of pages13
Volume25
ISBN (Print)9781713845393
Publication statusPublished - 6 Dec 2021
Event35th Conference on Neural Information Processing Systems, NeurIPS 2021 - Virtual
Duration: 6 Dec 202114 Dec 2021
https://nips.cc/Conferences/2021

Publication series

NameAdvances in Neural Information Processing Systems
Volume34
ISSN (Print)1049-5258
NameNeurIPS Proceedings

Conference

Conference35th Conference on Neural Information Processing Systems, NeurIPS 2021
Period6/12/2114/12/21
Internet address

Scopus Subject Areas

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing

Fingerprint

Dive into the research topics of 'TOHAN: A One-step Approach towards Few-shot Hypothesis Adaptation'. Together they form a unique fingerprint.

Cite this