Meta Discovery: Learning to Discover Novel Classes given Very Limited Data

Haoang Chi, Feng Liu, Bo Han, Wenjing Yang*, Long Lan*, Tongliang Liu, Gang Niu, Mingyuan Zhou, Masashi Sugiyama

*Corresponding author for this work

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

Abstract

In novel class discovery (NCD), we are given labeled data from seen classes and unlabeled data from unseen classes, and we train clustering models for the unseen classes. However, the implicit assumptions behind NCD are still unclear. In this paper, we demystify assumptions behind NCD and find that high-level semantic features should be shared among the seen and unseen classes. Based on this finding, NCD is theoretically solvable under certain assumptions and can be naturally linked to meta-learning that has exactly the same assumption as NCD. Thus, we can empirically solve the NCD problem by meta-learning algorithms after slight modifications. This meta-learning-based methodology significantly reduces the amount of unlabeled data needed for training and makes it more practical, as demonstrated in experiments. The use of very limited data is also justified by the application scenario of NCD: since it is unnatural to label only seen-class data, NCD is sampling instead of labeling in causality. Therefore, unseen-class data should be collected on the way of collecting seen-class data, which is why they are novel and first need to be clustered.
Original languageEnglish
Title of host publicationProceedings of Tenth International Conference on Learning Representations, ICLR 2022
PublisherInternational Conference on Learning Representations
Pages1-20
Number of pages20
Publication statusPublished - 25 Apr 2022
EventThe Tenth International Conference on Learning Representations, ICLR 2022 - Virtual
Duration: 25 Apr 202229 Apr 2022
https://iclr.cc/Conferences/2022
https://openreview.net/group?id=ICLR.cc/2022/Conference

Conference

ConferenceThe Tenth International Conference on Learning Representations, ICLR 2022
Period25/04/2229/04/22
Internet address

Fingerprint

Dive into the research topics of 'Meta Discovery: Learning to Discover Novel Classes given Very Limited Data'. Together they form a unique fingerprint.

Cite this