---
title: "Label Enhancement via Cross-View Fusion and Mixed Graph Propagation"
authors:
  - "Mengjiao Kai"
  - "Chao Tan"
  - "Yanda Wang"
  - "Juanna Zhai"
  - "Kang Wu"
  - "Ningkang Peng"
  - "Yanhui Gu"
doi: "10.24963/ijcai.2026/491"
url: "https://ijcai.org/proceedings/2026/491"
pdf: "https://ijcai.org/proceedings/2026/0491.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "4412-4420"
track: "Main Track"
keywords:
  - "Constraint Satisfaction and Optimization: Constraint satisfaction"
  - "Machine Learning: Attention models"
  - "Machine Learning: Multi-label learning"
  - "Data Mining: Exploratory data mining"
---

# Label Enhancement via Cross-View Fusion and Mixed Graph Propagation

Mengjiao Kai, Chao Tan, Yanda Wang, Juanna Zhai, Kang Wu, Ningkang Peng, Yanhui Gu

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 4412-4420. DOI: [10.24963/ijcai.2026/491](https://doi.org/10.24963/ijcai.2026/491)

## Abstract

Label Distribution Learning (LDL) effectively addresses label ambiguity by modeling the degree to which each label describes an instance. A key challenge in LDL is Label Enhancement (LE): recovering label distributions from logical labels. Existing LE methods typically treat logical labels as supervisory signals and learn a direct mapping from features to label distributions. However, they fail to fully exploit the rich information encoded in logical labels, limiting their performance. We propose CVMG (Cross-View Fusion and Mixed Graph-based Label Enhancement), a novel approach that addresses this limitation through two key innovations. First, we employ a cross-attention mechanism to integrate logical labels and features, leveraging their complementary information to generate enriched feature representations. Second, we construct a mixed dependency graph that captures both instance-level relationships from enhanced features and category-level dependencies from logical labels. Label distributions are then recovered through propagation over this graph. Extensive experiments on 13 real-world datasets demonstrate that CVMG significantly outperforms state-of-the-art methods, validating the effectiveness of our approach.