---
title: "Decoupled Imbalanced Label Distribution Learning"
authors:
  - "Yongbiao Gao"
  - "Xiangcheng Sun"
  - "Miaogen Ling"
  - "Chao Tan"
  - "Yi Zhai"
  - "Guohua Lv"
doi: "10.24963/ijcai.2025/579"
url: "https://ijcai.org/proceedings/2025/579"
pdf: "https://ijcai.org/proceedings/2025/0579.pdf"
venue: "Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"
year: 2025
pages: "5199-5207"
track: "Main Track"
keywords:
  - "Machine Learning: ML: Multi-label learning"
---

# Decoupled Imbalanced Label Distribution Learning

Yongbiao Gao, Xiangcheng Sun, Miaogen Ling, Chao Tan, Yi Zhai, Guohua Lv

*Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence*, pages 5199-5207. DOI: [10.24963/ijcai.2025/579](https://doi.org/10.24963/ijcai.2025/579)

## 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.