{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,18]],"date-time":"2026-01-18T10:12:49Z","timestamp":1768731169662,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":56,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,7,20]],"date-time":"2025-07-20T00:00:00Z","timestamp":1752969600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,20]]},"DOI":"10.1145\/3690624.3709249","type":"proceedings-article","created":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T18:44:43Z","timestamp":1743792283000},"page":"1984-1995","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Understanding and Mitigating Hyperbolic Dimensional Collapse in Graph Contrastive Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4185-8663","authenticated-orcid":false,"given":"Yifei","family":"Zhang","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong SAR, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1885-8051","authenticated-orcid":false,"given":"Hao","family":"Zhu","sequence":"additional","affiliation":[{"name":"Data61\/CSIRO, Sydney, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2510-5282","authenticated-orcid":false,"given":"Menglin","family":"Yang","sequence":"additional","affiliation":[{"name":"Yale University, New Haven, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8551-120X","authenticated-orcid":false,"given":"Jiahong","family":"Liu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong SAR, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5856-5229","authenticated-orcid":false,"given":"Rex","family":"Ying","sequence":"additional","affiliation":[{"name":"Yale University, New Haven, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8106-6447","authenticated-orcid":false,"given":"Irwin","family":"King","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong SAR, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6340-5289","authenticated-orcid":false,"given":"Piotr","family":"Koniusz","sequence":"additional","affiliation":[{"name":"Data61?CSIRO, Canberra, Australia & Australian National University, Canberra, Australia"}]}],"member":"320","published-online":{"date-parts":[[2025,7,20]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2013.77"},{"key":"e_1_3_2_2_2_1","volume-title":"Learning representations by maximizing mutual information across views. arXiv preprint arXiv:1906.00910","author":"Bachman Philip","year":"2019","unstructured":"Philip Bachman, R Devon Hjelm, and William Buchwalter. 2019. Learning representations by maximizing mutual information across views. arXiv preprint arXiv:1906.00910 (2019)."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2013.2254619"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2693418"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"crossref","unstructured":"James W Cannon William J Floyd Richard Kenyon Walter R Parry et al. 1997. Hyperbolic geometry. Flavors of geometry Vol. 31 59--115 (1997) 2.","DOI":"10.1017\/9781009701853.003"},{"key":"e_1_3_2_2_6_1","volume-title":"Hyperbolic graph convolutional neural networks. Advances in neural information processing systems","author":"Chami Ines","year":"2019","unstructured":"Ines Chami, Zhitao Ying, Christopher R\u00e9, and Jure Leskovec. 2019. Hyperbolic graph convolutional neural networks. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_2_7_1","volume-title":"International conference on machine learning. PMLR, 1597--1607","author":"Chen Ting","year":"2020","unstructured":"Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020b. A simple framework for contrastive learning of visual representations. In International conference on machine learning. PMLR, 1597--1607."},{"key":"e_1_3_2_2_8_1","volume-title":"Improved baselines with momentum contrastive learning. arXiv preprint arXiv:2003.04297","author":"Chen Xinlei","year":"2020","unstructured":"Xinlei Chen, Haoqi Fan, Ross Girshick, and Kaiming He. 2020a. Improved baselines with momentum contrastive learning. arXiv preprint arXiv:2003.04297 (2020)."},{"key":"e_1_3_2_2_9_1","first-page":"5088","article-title":"Learning log-determinant divergences for positive definite matrices","volume":"44","author":"Cherian Anoop","year":"2021","unstructured":"Anoop Cherian, Panagiotis Stanitsas, Jue Wang, Mehrtash Harandi, Vassilios Morellas, and Nikolaos Papanikolopoulos. 2021. Learning log-determinant divergences for positive definite matrices. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 44, 9 (2021), 5088--5102.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_2_10_1","volume-title":"Stabilizing Modality Gap & Lowering Gradient Norms Improve Zero-Shot Adversarial Robustness of VLMs. 31st SIGKDD Conference on Knowledge Discovery and Data Mining","author":"Dong Junhao","year":"2025","unstructured":"Junhao Dong, Piotr Koniusz, Xinghua Qu, and Yew-Soon Ong. 2025. Stabilizing Modality Gap & Lowering Gradient Norms Improve Zero-Shot Adversarial Robustness of VLMs. 31st SIGKDD Conference on Knowledge Discovery and Data Mining (2025)."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01834-6"},{"key":"e_1_3_2_2_12_1","volume-title":"International Conference on Machine Learning. PMLR, 1646--1655","author":"Ganea Octavian","year":"2018","unstructured":"Octavian Ganea, Gary B\u00e9cigneul, and Thomas Hofmann. 2018. Hyperbolic entailment cones for learning hierarchical embeddings. In International Conference on Machine Learning. PMLR, 1646--1655."},{"key":"e_1_3_2_2_13_1","volume-title":"Simcse: Simple contrastive learning of sentence embeddings. arXiv preprint arXiv:2104.08821","author":"Gao Tianyu","year":"2021","unstructured":"Tianyu Gao, Xingcheng Yao, and Danqi Chen. 2021. Simcse: Simple contrastive learning of sentence embeddings. arXiv preprint arXiv:2104.08821 (2021)."},{"key":"e_1_3_2_2_14_1","volume-title":"Matrix computations","author":"Golub Gene H","unstructured":"Gene H Golub and Charles F Van Loan. 2013. Matrix computations. JHU press."},{"key":"e_1_3_2_2_15_1","volume-title":"Zhaohan Guo, Mohammad Gheshlaghi Azar, et al.","author":"Grill Jean-Bastien","year":"2020","unstructured":"Jean-Bastien Grill, Florian Strub, Florent Altch\u00e9, Corentin Tallec, Pierre Richemond, Elena Buchatskaya, Carl Doersch, Bernardo Avila Pires, Zhaohan Guo, Mohammad Gheshlaghi Azar, et al. 2020. Bootstrap your own latent-a new approach to self-supervised learning. Advances in neural information processing systems, Vol. 33 (2020), 21271--21284."},{"key":"e_1_3_2_2_16_1","volume-title":"Graphcl: Contrastive self-supervised learning of graph representations. arXiv preprint arXiv:2007.08025","author":"Hafidi Hakim","year":"2020","unstructured":"Hakim Hafidi, Mounir Ghogho, Philippe Ciblat, and Ananthram Swami. 2020. Graphcl: Contrastive self-supervised learning of graph representations. arXiv preprint arXiv:2007.08025 (2020)."},{"key":"e_1_3_2_2_17_1","volume-title":"Pre-training with Random Orthogonal Projection Image Modeling. In The Twelfth International Conference on Learning Representations.","author":"Haghighat Maryam","year":"2024","unstructured":"Maryam Haghighat, Peyman Moghadam, Shaheer Mohamed, and Piotr Koniusz. 2024. Pre-training with Random Orthogonal Projection Image Modeling. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_2_18_1","volume-title":"Inductive representation learning on large graphs. Advances in neural information processing systems","author":"Hamilton Will","year":"2017","unstructured":"Will Hamilton, Zhitao Ying, and Jure Leskovec. 2017. Inductive representation learning on large graphs. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401063"},{"key":"e_1_3_2_2_20_1","volume-title":"Shervin Minaee, Radu Tudor Ionescu, and Nicu Sebe.","author":"Hondru Vlad","year":"2025","unstructured":"Vlad Hondru, Florinel Alin Croitoru, Shervin Minaee, Radu Tudor Ionescu, and Nicu Sebe. 2025. Masked Image Modeling: A Survey. arXiv: 2408.06687 (2025)."},{"key":"e_1_3_2_2_21_1","volume-title":"Understanding dimensional collapse in contrastive self-supervised learning. arXiv preprint arXiv:2110.09348","author":"Jing Li","year":"2021","unstructured":"Li Jing, Pascal Vincent, Yann LeCun, and Yuandong Tian. 2021. Understanding dimensional collapse in contrastive self-supervised learning. arXiv preprint arXiv:2110.09348 (2021)."},{"key":"e_1_3_2_2_22_1","volume-title":"Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907","author":"Kipf Thomas N","year":"2016","unstructured":"Thomas N Kipf and Max Welling. 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.82.036106"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3186150"},{"key":"e_1_3_2_2_25_1","volume-title":"Enhancing hyperbolic graph embeddings via contrastive learning. arXiv preprint arXiv:2201.08554","author":"Liu Jiahong","year":"2022","unstructured":"Jiahong Liu, Menglin Yang, Min Zhou, Shanshan Feng, and Philippe Fournier-Viger. 2022. Enhancing hyperbolic graph embeddings via contrastive learning. arXiv preprint arXiv:2201.08554 (2022)."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00648"},{"key":"e_1_3_2_2_27_1","volume-title":"Hyperbolic graph neural networks. Advances in neural information processing systems","author":"Liu Qi","year":"2019","unstructured":"Qi Liu, Maximilian Nickel, and Douwe Kiela. 2019a. Hyperbolic graph neural networks. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_2_28_1","unstructured":"Qi Liu Maximilian Nickel and Douwe Kiela. 2019b. Hyperbolic graph neural networks. In NeurIPS. 8230--8241."},{"key":"e_1_3_2_2_29_1","volume-title":"Chris J. Maddison, Ryota Tomioka, and Yee Whye Teh.","author":"Mathieu Emile","year":"2019","unstructured":"Emile Mathieu, Charline Le Lan, Chris J. Maddison, Ryota Tomioka, and Yee Whye Teh. 2019. Continuous Hierarchical Representations with Poincar\u00e9 Variational Auto-Encoders. In Advances in Neural Information Processing Systems, H. Wallach, H. Larochelle, A. Beygelzimer, F. dtextquotesingle Alch\u00e9-Buc, E. Fox, and R. Garnett (Eds.), Vol. 32. Curran Associates, Inc."},{"key":"e_1_3_2_2_30_1","volume-title":"Poincar\u00e9 embeddings for learning hierarchical representations. Advances in neural information processing systems","author":"Nickel Maximillian","year":"2017","unstructured":"Maximillian Nickel and Douwe Kiela. 2017. Poincar\u00e9 embeddings for learning hierarchical representations. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_2_31_1","article-title":"Brownian motion on manifolds with time-dependent metrics and stochastic completeness","volume":"61","author":"Paeng Seong-Hun","year":"2011","unstructured":"Seong-Hun Paeng. 2011. Brownian motion on manifolds with time-dependent metrics and stochastic completeness. Journal of Geometry and Physics, Vol. 61, 5 (2011).","journal-title":"Journal of Geometry and Physics"},{"key":"e_1_3_2_2_32_1","volume-title":"2007 15th European Signal Processing Conference. 606--610","author":"Roy Olivier","year":"2007","unstructured":"Olivier Roy and Martin Vetterli. 2007. The effective rank: A measure of effective dimensionality. In 2007 15th European Signal Processing Conference. 606--610."},{"key":"e_1_3_2_2_33_1","volume-title":"International symposium on graph drawing. Springer, 355--366","author":"Sarkar Rik","year":"2011","unstructured":"Rik Sarkar. 2011. Low distortion delaunay embedding of trees in hyperbolic plane. In International symposium on graph drawing. Springer, 355--366."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3450101"},{"key":"e_1_3_2_2_35_1","volume-title":"Fisher-Bures Adversary Graph Convolutional Networks. Conference on Uncertainty in Artificial Intelligence","volume":"115","author":"Sun Ke","year":"2019","unstructured":"Ke Sun, Piotr Koniusz, and Zhen Wang. 2019. Fisher-Bures Adversary Graph Convolutional Networks. Conference on Uncertainty in Artificial Intelligence, Vol. 115 (2019), 465--475."},{"key":"e_1_3_2_2_36_1","volume-title":"Poincarbackslash'e glove: Hyperbolic word embeddings. arXiv preprint arXiv:1810.06546","author":"Tifrea Alexandru","year":"2018","unstructured":"Alexandru Tifrea, Gary B\u00e9cigneul, and Octavian-Eugen Ganea. 2018. Poincarbackslash'e glove: Hyperbolic word embeddings. arXiv preprint arXiv:1810.06546 (2018)."},{"key":"e_1_3_2_2_37_1","volume-title":"On mutual information maximization for representation learning. arXiv preprint arXiv:1907.13625","author":"Tschannen Michael","year":"2019","unstructured":"Michael Tschannen, Josip Djolonga, Paul K Rubenstein, Sylvain Gelly, and Mario Lucic. 2019. On mutual information maximization for representation learning. arXiv preprint arXiv:1907.13625 (2019)."},{"key":"e_1_3_2_2_38_1","volume-title":"Graph attention networks. arXiv preprint arXiv:1710.10903","author":"Velickovic Petar","year":"2017","unstructured":"Petar Velickovic, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, and Yoshua Bengio. 2017. Graph attention networks. arXiv preprint arXiv:1710.10903 (2017)."},{"key":"e_1_3_2_2_39_1","unstructured":"Petar Velickovic William Fedus William L. Hamilton Pietro Li\u00f2 Yoshua Bengio and R. Devon Hjelm. 2019. Deep Graph Infomax. In ICLR."},{"key":"e_1_3_2_2_40_1","volume-title":"International Conference on Machine Learning. PMLR, 9929--9939","author":"Wang Tongzhou","year":"2020","unstructured":"Tongzhou Wang and Phillip Isola. 2020. Understanding contrastive representation learning through alignment and uniformity on the hypersphere. In International Conference on Machine Learning. PMLR, 9929--9939."},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331267"},{"key":"e_1_3_2_2_42_1","unstructured":"Wikipedia.org. 2024. Lagrange multiplier. https:\/\/en.wikipedia.org\/wiki\/Lagrange_multiplier"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512118"},{"key":"e_1_3_2_2_45_1","volume-title":"Hyperbolic Representation Learning: Revisiting and Advancing. arXiv preprint arXiv:2306.09118","author":"Yang Menglin","year":"2023","unstructured":"Menglin Yang, Min Zhou, Rex Ying, Yankai Chen, and Irwin King. 2023. Hyperbolic Representation Learning: Revisiting and Advancing. arXiv preprint arXiv:2306.09118 (2023)."},{"key":"e_1_3_2_2_46_1","volume-title":"Link prediction based on graph neural networks. Advances in neural information processing systems","author":"Zhang Muhan","year":"2018","unstructured":"Muhan Zhang and Yixin Chen. 2018. Link prediction based on graph neural networks. Advances in neural information processing systems, Vol. 31 (2018)."},{"key":"e_1_3_2_2_47_1","first-page":"1690","article-title":"Hyperbolic graph attention network","volume":"8","author":"Zhang Yiding","year":"2021","unstructured":"Yiding Zhang, Xiao Wang, Chuan Shi, Xunqiang Jiang, and Yanfang Ye. 2021. Hyperbolic graph attention network. IEEE Transactions on Big Data, Vol. 8, 6 (2021), 1690--1701.","journal-title":"IEEE Transactions on Big Data"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671914"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539425"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26336"},{"key":"e_1_3_2_2_51_1","first-page":"67533","article-title":"Mitigating the popularity bias of graph collaborative filtering: A dimensional collapse perspective","volume":"36","author":"Zhang Yifei","year":"2023","unstructured":"Yifei Zhang, Hao Zhu, Zixing Song, Piotr Koniusz, Irwin King, et al. 2023b. Mitigating the popularity bias of graph collaborative filtering: A dimensional collapse perspective. Advances in Neural Information Processing Systems, Vol. 36 (2023), 67533--67550.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482168"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00887"},{"key":"e_1_3_2_2_54_1","volume-title":"Advances in Neural Information Processing Systems","volume":"35","author":"Zhu Hao","year":"2022","unstructured":"Hao Zhu and Piotr Koniusz. 2022b. Generalized Laplacian Eigenmaps. In Advances in Neural Information Processing Systems, Vol. 35. Curran Associates, Inc., 30783--30797."},{"key":"e_1_3_2_2_55_1","first-page":"5682","article-title":"Contrastive laplacian eigenmaps","volume":"34","author":"Zhu Hao","year":"2021","unstructured":"Hao Zhu, Ke Sun, and Peter Koniusz. 2021. Contrastive laplacian eigenmaps. Advances in Neural Information Processing Systems, Vol. 34 (2021), 5682--5695.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_56_1","volume-title":"Deep graph contrastive representation learning. arXiv:2006.04131","author":"Zhu Yanqiao","year":"2020","unstructured":"Yanqiao Zhu, Yichen Xu, Feng Yu, Qiang Liu, Shu Wu, and Liang Wang. 2020. Deep graph contrastive representation learning. arXiv:2006.04131 (2020)."}],"event":{"name":"KDD '25: The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Toronto ON Canada","acronym":"KDD '25","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3690624.3709249","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3690624.3709249","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,16]],"date-time":"2025-08-16T15:41:02Z","timestamp":1755358862000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3690624.3709249"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,20]]},"references-count":56,"alternative-id":["10.1145\/3690624.3709249","10.1145\/3690624"],"URL":"https:\/\/doi.org\/10.1145\/3690624.3709249","relation":{},"subject":[],"published":{"date-parts":[[2025,7,20]]},"assertion":[{"value":"2025-07-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}