{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T14:49:57Z","timestamp":1782398997844,"version":"3.54.5"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T00:00:00Z","timestamp":1774310400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T00:00:00Z","timestamp":1782345600000},"content-version":"vor","delay-in-days":93,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J. King Saud Univ. Comput. Inf. Sci."],"published-print":{"date-parts":[[2026,7]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Hypergraphs have demonstrated remarkable advantages in numerous fields due to their capability to model multi-way correlations among an arbitrary number of vertices in complex data. However, existing contrastive learning-based methods face two core challenges in unsupervised hypergraph clustering. First, the uniform random sampling strategy is prone to introducing negative sampling bias under the message passing mechanism of hypergraphs. Second, the absence of explicit clustering-guided constraints results in a disconnection between representation learning and the clustering objective. To tackle these issues, a Cross-scale Hypergraph Contrastive Clustering (CHCC) framework is proposed in this paper. CHCC constructs a hierarchical discriminative system comprising \u201cmicro-scale nodes, meso-scale hyperedges, and macro-scale cluster prototypes.\u201d Specifically, via a node-level topological discrimination mechanism, this framework extends the contrastive objective from a \u201cnode-to-node\u201d paradigm to a \u201cnode-to-hyperedge\u201d one, fundamentally circumventing the sampling bias induced by false negatives. Simultaneously, a clustering-guided hyperedge semantic discrimination mechanism is introduced to achieve clustering-oriented feature optimization by contrasting local structural semantics with global cluster prototypes. Experimental results on six benchmark datasets demonstrate that CHCC outperforms existing state-of-the-art methods across multiple clustering metrics, comprehensively verifying its effectiveness in synergistically optimizing topology preservation and clustering performance.<\/jats:p>","DOI":"10.1007\/s44443-026-00674-x","type":"journal-article","created":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T13:49:09Z","timestamp":1774360149000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Cross-scale hypergraph contrastive clustering"],"prefix":"10.1007","volume":"38","author":[{"given":"Yuan","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junxiu","family":"An","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuze","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,3,24]]},"reference":[{"key":"674_CR1","doi-asserted-by":"crossref","unstructured":"Agarwal S, Lim J, Zelnik-Manor L, Perona P, Kriegman D, Belongie S (2005) Beyond pairwise clustering. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR\u201905) 2:838\u2013845. IEEE","DOI":"10.1109\/CVPR.2005.89"},{"issue":"1","key":"674_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3605776","volume":"56","author":"A Antelmi","year":"2023","unstructured":"Antelmi A, Cordasco G, Polato M, Scarano V, Spagnuolo C, Yang D (2023) A survey on hypergraph representation learning. ACM Comput Surv 56(1):1\u201338","journal-title":"ACM Comput Surv"},{"key":"674_CR3","unstructured":"Arya D, Gupta DK, Rudinac S, Worring M (2020) Hypersage: Generalizing inductive representation learning on hypergraphs. arXiv preprint arXiv:2010.04558"},{"key":"674_CR4","volume-title":"UCI machine learning repository","author":"A Asuncion","year":"2007","unstructured":"Asuncion A, Newman D et al (2007) UCI machine learning repository. Irvine, CA, USA"},{"key":"674_CR5","unstructured":"Chen T, Kornblith S, Norouzi M, Hinton G (2020) A simple framework for contrastive learning of visual representations. In: International conference on machine learning, pp 1597\u20131607. PmLR"},{"key":"674_CR6","unstructured":"Dong Y, Sawin W, Bengio Y (2020) Hnhn: Hypergraph networks with hyperedge neurons. arXiv preprint arXiv:2006.12278"},{"key":"674_CR7","doi-asserted-by":"crossref","unstructured":"Feng Y, You H, Zhang Z, Ji R, Gao Y (2019) Hypergraph neural networks. In: Proceedings of the AAAI conference on artificial intelligence 33:3558\u20133565","DOI":"10.1609\/aaai.v33i01.33013558"},{"key":"674_CR8","doi-asserted-by":"crossref","unstructured":"Giles CL, Bollacker KD, Lawrence S (1998) Citeseer: An automatic citation indexing system. In: Proceedings of the 3rd ACM conference on digital libraries, pp 89\u201398","DOI":"10.1145\/276675.276685"},{"key":"674_CR9","doi-asserted-by":"crossref","unstructured":"Hartigan JA, Wong MA (1979) Algorithm as 136: A k-means clustering algorithm. J Royal Stat Soc. Series c (applied statistics) 28(1):100\u2013108","DOI":"10.2307\/2346830"},{"issue":"3","key":"674_CR10","first-page":"2231","volume":"35","author":"Y Hu","year":"2021","unstructured":"Hu Y, Li X, Wang Y, Wu Y, Zhao Y, Yan C, Yin J, Gao Y (2021) Adaptive hypergraph auto-encoder for relational data clustering. IEEE Trans Knowl Data Eng 35(3):2231\u20132242","journal-title":"IEEE Trans Knowl Data Eng"},{"issue":"2","key":"674_CR11","doi-asserted-by":"publisher","first-page":"067","DOI":"10.1093\/bib\/bbae067","volume":"25","author":"L Hu","year":"2024","unstructured":"Hu L, Zhang M, Hu P, Zhang J, Niu C, Lu X, Jiang X, Ma Y (2024) Dual-channel hypergraph convolutional network for predicting herb-disease associations. Brief Bioinform 25(2):067","journal-title":"Brief Bioinform"},{"key":"674_CR12","unstructured":"Kingma DP (2014) Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980"},{"key":"674_CR13","unstructured":"Kipf T (2016) Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907"},{"key":"674_CR14","unstructured":"Kipf TN, Welling M (2016) Variational graph auto-encoders. arXiv preprint arXiv:1611.07308"},{"key":"674_CR15","doi-asserted-by":"crossref","unstructured":"Lee D, Shin K (2023) I\u2019m me, we\u2019re us, and i\u2019m us: Tri-directional contrastive learning on hypergraphs. In: Proceedings of the AAAI conference on artificial intelligence 37:8456\u20138464","DOI":"10.1609\/aaai.v37i7.26019"},{"key":"674_CR16","doi-asserted-by":"crossref","unstructured":"Lee J, Chae D-K (2024) Multi-view mixed attention for contrastive learning on hypergraphs. In: Proceedings of the 47th international ACM SIGIR conference on research and development in information retrieval, pp 2543\u20132547","DOI":"10.1145\/3626772.3657897"},{"issue":"6","key":"674_CR17","doi-asserted-by":"publisher","first-page":"1303","DOI":"10.1109\/TPAMI.2019.2895608","volume":"42","author":"X Liu","year":"2019","unstructured":"Liu X, Wang L, Zhu X, Li M, Zhu E, Liu T, Liu L, Dou Y, Yin J (2019) Absent multiple kernel learning algorithms. IEEE Trans Pattern Anal Mach Intell 42(6):1303\u20131316","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"674_CR18","unstructured":"Maaten Lvd, Hinton G (2008) Visualizing data using t-sne. J Mach Learn Res 9(Nov), pp 2579\u20132605"},{"issue":"2","key":"674_CR19","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1023\/A:1009953814988","volume":"3","author":"AK McCallum","year":"2000","unstructured":"McCallum AK (2000) Nigam K, Rennie J, Seymore K: Automating the construction of internet portals with machine learning. Inf Retrieval 3(2):127\u2013163","journal-title":"Inf Retrieval"},{"key":"674_CR20","doi-asserted-by":"crossref","unstructured":"Mengran L, Xinglin P, Yong Z, Yongli H, Baocai Y (2022) Shcn: Self-supervised general hypergraph clustering network. In: 2022 IEEE international conference on big data (Big Data), pp 1298\u20131303. IEEE","DOI":"10.1109\/BigData55660.2022.10020643"},{"key":"674_CR21","unstructured":"Oord Avd, Li Y, Vinyals O (2018) Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748"},{"key":"674_CR22","doi-asserted-by":"crossref","unstructured":"Qian Y, Ma T, Zhang C Ye Y (2024) Dual-level hypergraph contrastive learning with adaptive temperature enhancement. In: Companion proceedings of the ACM web conference 2024, pp 859\u2013862","DOI":"10.1145\/3589335.3651493"},{"issue":"9","key":"674_CR23","doi-asserted-by":"publisher","first-page":"4515","DOI":"10.1109\/TKDE.2024.3380643","volume":"36","author":"Y Song","year":"2024","unstructured":"Song Y, Gu Y, Li T, Qi J, Liu Z, Jensen CS, Yu G (2024) Chgnn: A semi-supervised contrastive hypergraph learning network. IEEE Trans Knowl Data Eng 36(9):4515\u20134530","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"674_CR24","doi-asserted-by":"crossref","unstructured":"Chen D-Y, Tian X-P, Shen Y-T, Ouhyoung M (2003) On visual similarity based 3d model retrieval. In: Computer graphics forum 22:223\u2013232. Wiley Online Library","DOI":"10.1111\/1467-8659.00669"},{"key":"674_CR25","doi-asserted-by":"crossref","unstructured":"Tu K, Cui P, Wang X, Wang F, Zhu W (2018) Structural deep embedding for hyper-networks. In: Proceedings of the AAAI conference on artificial intelligence, vol 32","DOI":"10.1609\/aaai.v32i1.11266"},{"key":"674_CR26","unstructured":"Veli\u010dkovi\u0107 P, Cucurull G, Casanova A, Romero A, Lio P, Bengio Y: Graph attention networks. arXiv preprint arXiv:1710.10903 (2017)"},{"key":"674_CR27","doi-asserted-by":"crossref","unstructured":"Wan S, Zhan Y, Chen S, Pan S, Yang J, Tao D, Gong C (2023) Boosting graph contrastive learning via adaptive sampling. IEEE transactions on neural networks and learning systems","DOI":"10.1109\/TNNLS.2023.3291358"},{"key":"674_CR28","doi-asserted-by":"crossref","unstructured":"Wang Q, Zhao B, Ding Z, Feng W, Gao Q (2025) Hypergraph clustering network with partial attribute imputation. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 2697\u20132706","DOI":"10.1109\/ICCV51701.2025.00259"},{"key":"674_CR29","doi-asserted-by":"publisher","first-page":"1909","DOI":"10.52202\/068431-0139","volume":"35","author":"T Wei","year":"2022","unstructured":"Wei T, You Y, Chen T, Shen Y, He J, Wang Z (2022) Augmentations in hypergraph contrastive learning: Fabricated and generative. Adv Neural Inf Process Syst 35:1909\u20131922","journal-title":"Adv Neural Inf Process Syst"},{"key":"674_CR30","unstructured":"Xia J, Wu L, Wang G, Chen J, Li SZ (2021) Progcl: Rethinking hard negative mining in graph contrastive learning. arXiv preprint arXiv:2110.02027"},{"key":"674_CR31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.neunet.2021.10.006","volume":"145","author":"W Xia","year":"2022","unstructured":"Xia W, Wang S, Yang M, Gao Q, Han J, Gao X (2022) Multi-view graph embedding clustering network: Joint self-supervision and block diagonal representation. Neural Netw 145:1\u20139","journal-title":"Neural Netw"},{"key":"674_CR32","unstructured":"Xu K, Hu W, Leskovec J, Jegelka S (2018) How powerful are graph neural networks? arXiv preprint arXiv:1810.00826"},{"key":"674_CR33","unstructured":"Yang Z, Cohen W, Salakhudinov R (2016) Revisiting semi-supervised learning with graph embeddings. In: International conference on machine learning, pp 40\u201348. PMLR"},{"key":"674_CR34","doi-asserted-by":"crossref","unstructured":"Yang X, Tan C, Liu Y, Liang K, Wang S, Zhou S, Xia J, Li SZ, Liu X, Zhu E (2023) Convert: Contrastive graph clustering with reliable augmentation. In: Proceedings of the 31st ACM international conference on multimedia, pp 319\u2013327","DOI":"10.1145\/3581783.3611809"},{"key":"674_CR35","unstructured":"Zhang R, Zou Y, Ma J (2019) Hyper-sagnn: a self-attention based graph neural network for hypergraphs. arXiv preprint arXiv:1911.02613"},{"key":"674_CR36","doi-asserted-by":"crossref","unstructured":"Zhao H, Yang X, Wang Z, Yang E, Deng C (2021) Graph debiased contrastive learning with joint representation clustering. In: IJCAI, pp 3434\u20133440","DOI":"10.24963\/ijcai.2021\/473"},{"issue":"4","key":"674_CR37","doi-asserted-by":"publisher","first-page":"1351","DOI":"10.1109\/TNNLS.2019.2919900","volume":"31","author":"S Zhou","year":"2019","unstructured":"Zhou S, Liu X, Li M, Zhu E, Liu L, Zhang C, Yin J (2019) Multiple kernel clustering with neighbor-kernel subspace segmentation. IEEE Trans Neural Netw Learn Syst 31(4):1351\u20131362","journal-title":"IEEE Trans Neural Netw Learn Syst"}],"container-title":["Journal of King Saud University Computer and Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s44443-026-00674-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44443-026-00674-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44443-026-00674-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T14:12:46Z","timestamp":1782396766000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s44443-026-00674-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,24]]},"references-count":37,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,7]]}},"alternative-id":["674"],"URL":"https:\/\/doi.org\/10.1007\/s44443-026-00674-x","relation":{},"ISSN":["1319-1578","2213-1248"],"issn-type":[{"value":"1319-1578","type":"print"},{"value":"2213-1248","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,24]]},"assertion":[{"value":"3 January 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 March 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 March 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"260"}}