---
title: "Dual Branch Mutual Teaching for Long-Tailed Partial Label Learning"
authors:
  - "Xiangyu Ren"
  - "Mingxuan Xia"
  - "Guangcheng Zhu"
  - "Gengyu Lyu"
  - "Haobo Wang"
  - "Peng Lu"
doi: "10.24963/ijcai.2026/528"
url: "https://ijcai.org/proceedings/2026/528"
pdf: "https://ijcai.org/proceedings/2026/0528.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "4741-4749"
track: "Main Track"
keywords:
  - "Machine Learning: Weakly supervised learning"
---

# Dual Branch Mutual Teaching for Long-Tailed Partial Label Learning

Xiangyu Ren, Mingxuan Xia, Guangcheng Zhu, Gengyu Lyu, Haobo Wang, Peng Lu

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 4741-4749. DOI: [10.24963/ijcai.2026/528](https://doi.org/10.24963/ijcai.2026/528)

## 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.