{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/dual-level-hypergraph-contrastive-learning","title":"Dual-level Hypergraph Contrastive Learning with Adaptive Temperature Enhancement","arxiv_id":null,"date":"2024-05-14","proceeding":"International World Wide Web Conference 2024 5","authors":["Yiyue Qian","Tianyi Ma","Chuxu Zhang","Yanfang Ye"],"abstract":"Inspired by the success of graph contrastive learning, researchers have begun exploring the benefits of contrastive learning over hypergraphs. However, these works have the following limitations in modeling the high-order relationships over unlabeled data: (i) They primarily focus on maximizing the agreements among individual node embeddings while neglecting the capture of group-wise collective behaviors within hypergraphs; (ii) Most of them disregard the importance of the temperature index in discriminating contrastive pairs during contrast optimization. To address these limitations, we propose a novel dual-level Hy perG raph C ontrastive L earning framework with Ad aptive T emperature (HyGCL-AdT ) to boost contrastive learning over hypergraphs. Specifically, unlike most works that merely maximize the agreement of node embeddings in hypergraphs, we propose a dual-level contrast mechanism that not only captures the individual node behaviors in a local context but also models the group-wise collective behaviors of nodes within hyperedges from a community perspective. Besides, we design an adaptive temperature-enhanced contrastive optimization to improve the discrimination ability between contrastive pairs. Empirical experiments conducted on seven benchmark hypergraphs demonstrate that HyGCL-AdT exhibits excellent effectiveness compared to state-of-the-art baseline models. The source code is available at https://github.com/graphprojects/HyGCL-AdT.","url_abs":"https://dl.acm.org/doi/10.1145/3589335.3651493","url_pdf":"https://dl.acm.org/doi/pdf/10.1145/3589335.3651493","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"dual-level-hypergraph-contrastive-learning","repo_url":"https://github.com/graphprojects/HyGCL-AdT","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"hypergraph-contrastive-learning","task_name":"Hypergraph Contrastive Learning"},{"task_slug":"hypergraph-representations","task_name":"Hypergraph representations"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/hypergraph-contrastive-learning-on-twitter","task":"Hypergraph Contrastive Learning","dataset":"Twitter-HyDrug-UR","model":"HyGCL-AdT","rank_in_archive_order":1,"of":1,"metrics":{"Accuray":"68.76 ± 0.41"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}