Universal Semi-Supervised Learning

Zhuo Huang, Chao Xue, Bo Han, Jian Yang, Chen Gong*

*Corresponding author for this work

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

1 Citation (Scopus)

Abstract

Universal Semi-Supervised Learning (UniSSL) aims to solve the open-set problem where both the class distribution (i.e., class set) and feature distribution (i.e., feature domain) are different between labeled dataset and unlabeled dataset. Such a problem seriously hinders the realistic landing of classical SSL. Different from the existing SSL methods targeting at the open-set problem that only study one certain scenario of class distribution mismatch and ignore the feature distribution mismatch, we consider a more general case where a mismatch exists in both class and feature distribution. In this case, we propose a “Class-shAring data detection and Feature Adaptation” (CAFA) framework which requires no prior knowledge of the class relationship between the labeled dataset and unlabeled dataset. Particularly, CAFA utilizes a novel scoring strategy to detect the data in the shared class set. Then, it conducts domain adaptation to fully exploit the value of the detected class-sharing data for better semi-supervised consistency training. Exhaustive experiments on several benchmark datasets show the effectiveness of our method in tackling open-set problems.

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
Pages26714-26725
Number of pages12
Volume32
ISBN (Electronic)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 'Universal Semi-Supervised Learning'. Together they form a unique fingerprint.

Cite this