{"type":"ScholarlyArticle","title":"Dual Branch Mutual Teaching for Long-Tailed Partial Label Learning","authors":[{"name":"Xiangyu Ren","slug":"xiangyu-ren","given":"Xiangyu","family":"Ren","affiliation":""},{"name":"Mingxuan Xia","slug":"mingxuan-xia","given":"Mingxuan","family":"Xia","affiliation":""},{"name":"Guangcheng Zhu","slug":"guangcheng-zhu","given":"Guangcheng","family":"Zhu","affiliation":""},{"name":"Gengyu Lyu","slug":"gengyu-lyu","given":"Gengyu","family":"Lyu","affiliation":""},{"name":"Haobo Wang","slug":"haobo-wang","given":"Haobo","family":"Wang","affiliation":""},{"name":"Peng Lu","slug":"peng-lu","given":"Peng","family":"Lu","affiliation":""}],"abstract":"In Partial Label Learning (PLL), each instance is associated with a candidate label set, with exactly one label being true. While most studies implicitly assume balanced class distributions, real-world data often exhibit severe class imbalance distributions, leading to the Long-Tailed Partial Label Learning (LT-PLL) problem. In response, prevailing strategies typically manifest the label space to retrieve more tail samples for improved pseudo-label accuracy. However, hard-to-distinguish tail samples can significantly hinder representation learning and, in turn, affect the quality of pseudo-labels. To address this, we propose a novel Distribution-aware Dual-branch Contrastive Learning framework, DEACON, that decouples representation of head and tail labels via a dual-branch mutual-teaching design, enabling disambiguation across different shot-level groups with tailored representations. DEACON comprises two modules: (i)-a instance-balanced branch trained with a vanilla contrastive objective; (ii)-a label-balanced branch trained with a novel reweighted loss that adjusts the contrastive strength through the conditioned von-Mises Fisher density. The two branches mutually teach each other using their pseudo-labels, and we ensemble their predictions to improve overall performance. Extensive experiments on various benchmarks show that our method consistently outperforms state-of-the-art baselines.Code and appendix can be found in https://github.com/YukiNozzzz/DEACON.","doi":"10.24963/ijcai.2026/528","url":"https://ijcai.org/proceedings/2026/528","pdf":"https://ijcai.org/proceedings/2026/0528.pdf","markdown":"https://ijcai.org/proceedings/2026/528.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/528","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"Machine Learning","track":"Main Track","number":528,"pages":{"first":4741,"last":4749},"keywords":["Machine Learning: Weakly supervised learning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}