{"type":"ScholarlyArticle","title":"Learning from Complementary Labels via Partial-Output Consistency Regularization","authors":[{"name":"Deng-Bao Wang","slug":"deng-bao-wang","given":"Deng-Bao","family":"Wang","affiliation":""},{"name":"Lei Feng","slug":"lei-feng","given":"Lei","family":"Feng","affiliation":""},{"name":"Min-Ling Zhang","slug":"min-ling-zhang","given":"Min-Ling","family":"Zhang","affiliation":""}],"abstract":"In complementary-label learning (CLL), a multi-class classifier is learned from training instances each associated with complementary labels, which specify the classes that the instance does not belong to. Previous studies focus on unbiased risk estimator or surrogate loss while neglect the importance of regularization in training phase. In this paper, we give the first attempt to leverage regularization techniques for CLL. By decoupling a label vector into complementary labels and partial unknown labels, we simultaneously inhibit the outputs of complementary labels with a complementary loss and penalize the sensitivity of the classifier on the partial outputs of these unknown classes by consistency regularization. Then we unify the complementary loss and consistency loss together by a specially designed dynamic weighting factor. We conduct a series of experiments showing that the proposed method achieves highly competitive performance in CLL.","doi":"10.24963/ijcai.2021/423","url":"https://ijcai.org/proceedings/2021/423","pdf":"https://ijcai.org/proceedings/2021/0423.pdf","markdown":"https://ijcai.org/proceedings/2021/423.md","bibtex":"https://ijcai.org/proceedings/2021/bibtex/423","volume":{"slug":"2021","title":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2021","url":"https://ijcai.org/proceedings/2021/","year":2021,"location":"Montreal","dates":"19-27 August 2021","editors":"Prof. Zhi-Hua Zhou","isbn":"978-0-9992411-9-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2021"},"section":"Machine Learning","track":"Main Track","number":423,"pages":{"first":3075,"last":3081},"keywords":["Machine Learning: Classification","Machine Learning: Weakly Supervised Learning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}