{"type":"ScholarlyArticle","title":"Decoupled Imbalanced Label Distribution Learning","authors":[{"name":"Yongbiao Gao","slug":"yongbiao-gao","given":"Yongbiao","family":"Gao","affiliation":""},{"name":"Xiangcheng Sun","slug":"xiangcheng-sun","given":"Xiangcheng","family":"Sun","affiliation":""},{"name":"Miaogen Ling","slug":"miaogen-ling","given":"Miaogen","family":"Ling","affiliation":""},{"name":"Chao Tan","slug":"chao-tan","given":"Chao","family":"Tan","affiliation":""},{"name":"Yi Zhai","slug":"yi-zhai","given":"Yi","family":"Zhai","affiliation":""},{"name":"Guohua Lv","slug":"guohua-lv","given":"Guohua","family":"Lv","affiliation":""}],"abstract":"Label Distribution Learning (LDL) has been successfully implemented in numerous practical applications. However, the imbalance in label distributions presents a significant challenge due to the substantial variation in annotation information. To tackle this issue, we introduce Decoupled Imbalance Label Distribution Learning (DILDL), which decomposes the imbalanced label distribution into a dominant label distribution and a non-dominant label distribution. Our empirical findings reveal that an excessively high description degree of dominant labels can result in substantial gradient information attenuation for non-dominant labels during the learning process. Therefore, we employ the decoupling approach to balance the description degrees of both dominant and non-dominant labels independently. Furthermore, we align the feature representations with the representations of dominant and non-dominant labels separately, aiming to effectively mitigate the distribution shift problem. Experimental results demonstrate that our proposed DILDL outperforms other state-of-the-art methods for imbalance label distribution learning.","doi":"10.24963/ijcai.2025/579","url":"https://ijcai.org/proceedings/2025/579","pdf":"https://ijcai.org/proceedings/2025/0579.pdf","markdown":"https://ijcai.org/proceedings/2025/579.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/579","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"Machine Learning","track":"Main Track","number":579,"pages":{"first":5199,"last":5207},"keywords":["Machine Learning: ML: Multi-label learning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}