{"type":"ScholarlyArticle","title":"Semi-supervised Clustering via Adversarially Enhanced Intent Propagation","authors":[{"name":"Wentao Zhong","slug":"wentao-zhong","given":"Wentao","family":"Zhong","affiliation":""},{"name":"Ruina Bai","slug":"ruina-bai","given":"Ruina","family":"Bai","affiliation":""},{"name":"Jingjing Xue","slug":"jingjing-xue","given":"Jingjing","family":"Xue","affiliation":""},{"name":"Ying Nie","slug":"ying-nie","given":"Ying","family":"Nie","affiliation":""},{"name":"Ruizhang Huang","slug":"ruizhang-huang","given":"Ruizhang","family":"Huang","affiliation":""}],"abstract":"Semi-supervised clustering (SSC) enables personalized clustering under limited user supervision. Given the sparsity of initial user intents, constraint propagation has been proposed as a powerful approach to explore and generate new performance-enhancing constraints. However, existing methods struggle to handle a large number of ``gray samples'' that deviate from initial supervision signals and exhibit ambiguous semantics with indistinct boundaries. Compared with ``distinct samples'' that closely match the supervision, gray samples typically contain richer latent semantics, and accurately identifying their relational types can significantly improve clustering performance. To address this challenge, we propose Adversarially Enhanced Propagation-driven Intent-aware Clustering (AEPIC). Specifically, we design an Adversarially Enhanced Constraint Propagation (AECP) mechanism that leverages global adversarial learning over dual relational links to identify gray samples and expand them into meaningful pseudo-user intents. In addition, an intent-aware regularization strategy integrates these pseudo-user intents into representation learning and clustering optimization, further improving clustering performance. Experiments on 5 benchmark datasets demonstrate that, under sparse supervision, AEPIC consistently outperforms state-of-the-art semi-supervised clustering methods.","doi":"10.24963/ijcai.2026/680","url":"https://ijcai.org/proceedings/2026/680","pdf":"https://ijcai.org/proceedings/2026/0680.pdf","markdown":"https://ijcai.org/proceedings/2026/680.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/680","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":"Natural Language Processing","track":"Main Track","number":680,"pages":{"first":6109,"last":6117},"keywords":["Machine Learning: Clustering","Natural Language Processing: Information retrieval and text mining","Machine Learning: Deep learning architectures","Machine Learning: Feature extraction, selection and dimensionality reduction"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}