{"type":"ScholarlyArticle","title":"Multi-Label Text Classification with Label Attention Aware and Correlation Aware Contrastive Learning","authors":[{"name":"Zhengzhong Zhu","slug":"zhengzhong-zhu","given":"Zhengzhong","family":"Zhu","affiliation":""},{"name":"Pei Zhou","slug":"pei-zhou","given":"Pei","family":"Zhou","affiliation":""},{"name":"Zeting Li","slug":"zeting-li","given":"Zeting","family":"Li","affiliation":""},{"name":"Kejiang Chen","slug":"kejiang-chen","given":"Kejiang","family":"Chen","affiliation":""},{"name":"Jiangping Zhu","slug":"jiangping-zhu","given":"Jiangping","family":"Zhu","affiliation":""}],"abstract":"Multi-label text classification (MLTC) is a challenging task where each document can be associated with multiple interdependent labels. This task is complicated by two key issues: the intricate correlations among labels and the partial overlap between labels and text relevance. Existing methods often fail to capture the semantic dependencies between labels or struggle to handle the ambiguities caused by partial overlaps, resulting in suboptimal representation learning.\r\nTo address these challenges, we propose the Unified Contextual and Label-Aware Framework (UCLAF), which integrates a Label Attention Aware Network(LAN) and Correlation Aware Contrastive Learning (CACL) in a synergistic design. The Label Attention Aware Network explicitly models label dependencies by embedding labels and texts into a shared semantic space, aligning text representations with label semantics. Meanwhile, Correlation Aware Contrastive Learning refines these representations by dynamically modeling sample-level relationships, leveraging a contrastive loss function that accounts for the proportional overlap of labels between samples. This complementary approach enables UCLAF to jointly address complex label correlations and partial label overlaps.\r\nExtensive experiments on benchmark datasets demonstrate that UCLAF significantly outperforms state-of-the-art methods, showcasing its effectiveness in improving both representation learning and classification performance in MLTC tasks. We will release our code after the paper is accepted.","doi":"10.24963/ijcai.2025/936","url":"https://ijcai.org/proceedings/2025/936","pdf":"https://ijcai.org/proceedings/2025/0936.pdf","markdown":"https://ijcai.org/proceedings/2025/936.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/936","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"Natural Language Processing","track":"Main Track","number":936,"pages":{"first":8420,"last":8428},"keywords":["Natural Language Processing: NLP: Text classification"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}