Label Enhancement via Cross-View Fusion and Mixed Graph Propagation
Mengjiao Kai, Chao Tan, Yanda Wang, Juanna Zhai, Kang Wu, Ningkang Peng, Yanhui Gu
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.
BibTeX
@inproceedings{ijcai2026_labelenhancement,
title = {Label Enhancement via Cross-View Fusion and Mixed Graph Propagation},
author = {Mengjiao Kai and Chao Tan and Yanda Wang and Juanna Zhai and Kang Wu and Ningkang Peng and Yanhui Gu},
booktitle = {IJCAI 2026},
year = {2026}
}