A Universal Unbiased Method for Classification from Aggregate Observations

Zixi Wei, Lei Feng*, Bo Han, Tongliang Liu, Gang Niu, Xiaofeng Zhu, Heng Tao Shen

*Corresponding author for this work

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

2 Citations (Scopus)

Abstract

In conventional supervised classification, true labels are required for individual instances. However, it could be prohibitive to collect the true labels for individual instances, due to privacy concerns or unaffordable annotation costs. This motivates the study on classification from aggregate observations (CFAO), where the supervision is provided to groups of instances, instead of individual instances. CFAO is a generalized learning framework that contains various learning problems, such as multiple-instance learning and learning from label proportions. The goal of this paper is to present a novel universal method of CFAO, which holds an unbiased estimator of the classification risk for arbitrary losses-previous research failed to achieve this goal. Practically, our method works by weighing the importance of each label for each instance in the group, which provides purified supervision for the classifier to learn. Theoretically, our proposed method not only guarantees the risk consistency due to the unbiased risk estimator but also can be compatible with arbitrary losses. Extensive experiments on various problems of CFAO demonstrate the superiority of our proposed method.

Original languageEnglish
Title of host publicationProceedings of 40th International Conference on Machine Learning, ICML 2023
EditorsAndreas Krause, Emma Brunskill, Kyunghyun Cho, Barbara Engelhardt, Sivan Sabato, Jonathan Scarlett
PublisherML Research Press
Pages36804-36820
Number of pages17
Publication statusPublished - Jul 2023
Event40th International Conference on Machine Learning, ICML 2023 - Honolulu, United States
Duration: 23 Jul 202329 Jul 2023
https://icml.cc/Conferences/2023
https://proceedings.mlr.press/v202/
https://openreview.net/group?id=ICML.cc/2023/Conference

Publication series

NameProceedings of Machine Learning Research
PublisherML Research Press
Volume202
ISSN (Print)2640-3498

Conference

Conference40th International Conference on Machine Learning, ICML 2023
Country/TerritoryUnited States
CityHonolulu
Period23/07/2329/07/23
Internet address

Scopus Subject Areas

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

Fingerprint

Dive into the research topics of 'A Universal Unbiased Method for Classification from Aggregate Observations'. Together they form a unique fingerprint.

Cite this