DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lee, Hyuck | ko |
dc.contributor.author | Shin, Seungjae | ko |
dc.contributor.author | Kim, Heeyoung | ko |
dc.date.accessioned | 2022-12-13T07:01:22Z | - |
dc.date.available | 2022-12-13T07:01:22Z | - |
dc.date.created | 2022-12-12 | - |
dc.date.created | 2022-12-12 | - |
dc.date.issued | 2021-12-08 | - |
dc.identifier.citation | 35th Conference on Neural Information Processing Systems, NeurIPS 2021, pp.7082 - 7094 | - |
dc.identifier.issn | 1049-5258 | - |
dc.identifier.uri | http://hdl.handle.net/10203/302925 | - |
dc.description.abstract | Existing semi-supervised learning (SSL) algorithms typically assume class-balanced datasets, although the class distributions of many real-world datasets are imbalanced. In general, classifiers trained on a class-imbalanced dataset are biased toward the majority classes. This issue becomes more problematic for SSL algorithms because they utilize the biased prediction of unlabeled data for training. However, traditional class-imbalanced learning techniques, which are designed for labeled data, cannot be readily combined with SSL algorithms. We propose a scalable class-imbalanced SSL algorithm that can effectively use unlabeled data, while mitigating class imbalance by introducing an auxiliary balanced classifier (ABC) of a single layer, which is attached to a representation layer of an existing SSL algorithm. The ABC is trained with a class-balanced loss of a minibatch, while using high-quality representations learned from all data points in the minibatch using the backbone SSL algorithm to avoid overfitting and information loss. Moreover, we use consistency regularization, a recent SSL technique for utilizing unlabeled data in a modified way, to train the ABC to be balanced among the classes by selecting unlabeled data with the same probability for each class. The proposed algorithm achieves state-of-the-art performance in various class-imbalanced SSL experiments using four benchmark datasets. | - |
dc.language | English | - |
dc.publisher | Neural Information Processing Systems Foundation | - |
dc.title | ABC: Auxiliary Balanced Classifier for Class-imbalanced Semi-supervised Learning | - |
dc.type | Conference | - |
dc.identifier.wosid | 000901616400007 | - |
dc.identifier.scopusid | 2-s2.0-85125031649 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 7082 | - |
dc.citation.endingpage | 7094 | - |
dc.citation.publicationname | 35th Conference on Neural Information Processing Systems, NeurIPS 2021 | - |
dc.identifier.conferencecountry | US | - |
dc.identifier.conferencelocation | Virtual | - |
dc.contributor.localauthor | Kim, Heeyoung | - |
dc.contributor.nonIdAuthor | Lee, Hyuck | - |
dc.contributor.nonIdAuthor | Shin, Seungjae | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.