{"type":"ScholarlyArticle","title":"Label Enhancement via Cross-View Fusion and Mixed Graph Propagation","authors":[{"name":"Mengjiao Kai","slug":"mengjiao-kai","given":"Mengjiao","family":"Kai","affiliation":""},{"name":"Chao Tan","slug":"chao-tan","given":"Chao","family":"Tan","affiliation":""},{"name":"Yanda Wang","slug":"yanda-wang","given":"Yanda","family":"Wang","affiliation":""},{"name":"Juanna Zhai","slug":"juanna-zhai","given":"Juanna","family":"Zhai","affiliation":""},{"name":"Kang Wu","slug":"kang-wu","given":"Kang","family":"Wu","affiliation":""},{"name":"Ningkang Peng","slug":"ningkang-peng","given":"Ningkang","family":"Peng","affiliation":""},{"name":"Yanhui Gu","slug":"yanhui-gu","given":"Yanhui","family":"Gu","affiliation":""}],"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.","doi":"10.24963/ijcai.2026/491","url":"https://ijcai.org/proceedings/2026/491","pdf":"https://ijcai.org/proceedings/2026/0491.pdf","markdown":"https://ijcai.org/proceedings/2026/491.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/491","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":491,"pages":{"first":4412,"last":4420},"keywords":["Constraint Satisfaction and Optimization: Constraint satisfaction","Machine Learning: Attention models","Machine Learning: Multi-label learning","Data Mining: Exploratory data mining"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}