{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T18:07:31Z","timestamp":1757614051115,"version":"3.44.0"},"reference-count":47,"publisher":"Association for Computing Machinery (ACM)","issue":"11","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Proc. VLDB Endow."],"published-print":{"date-parts":[[2025,7]]},"abstract":"<jats:p>\n            An attributed hypergraph comprises nodes with attributes and hyperedges that connect varying numbers of nodes.\n            <jats:italic toggle=\"yes\">Attributed hypergraph node and hyperedge embedding<\/jats:italic>\n            (AHNEE) maps nodes and hyperedges to compact vectors for use in important tasks such as node classification, hyperedge link prediction, and hyperedge classification. Generating high-quality embeddings is challenging due to the complexity of attributed hypergraphs and the need to embed both nodes and hyperedges, especially in large-scale data. Existing solutions often fall short by focusing only on nodes or lacking native support for attributed hypergraphs, leading to inferior quality, and struggle with scalability on large attributed hypergraphs.\n          <\/jats:p>\n          <jats:p>We propose SAHE, an efficient and effective approach that unifies node and hyperedge embeddings for AHNEE computation, advancing the state of the art via comprehensive embedding formulations and algorithmic designs. First, we introduce two higher-order similarity measures, HMS-N and HMS-E, to capture similarities between node pairs and hyperedge pairs, respectively. These measures consider multi-hop connections and global topology within an extended hypergraph that incorporates attribute-based hyperedges. SAHE formulates the AHNEE objective to jointly preserve all-pair HMS-N and HMS-E similarities. Direct optimization is computationally expensive, so we analyze and unify core approximations of all-pair HMS-N and HMS-E to solve them simultaneously. To enhance efficiency, we design several non-trivial optimizations that avoid iteratively materializing large dense matrices while maintaining high-quality results. Extensive experiments on diverse attributed hypergraphs and 3 downstream tasks, compared against 11 baselines, show that SAHE consistently outperforms existing methods in embedding quality and is up to orders of magnitude faster.<\/jats:p>","DOI":"10.14778\/3749646.3749692","type":"journal-article","created":{"date-parts":[[2025,9,4]],"date-time":"2025-09-04T17:55:06Z","timestamp":1757008506000},"page":"4269-4281","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Effective and Efficient Attributed Hypergraph Embedding on Nodes and Hyperedges"],"prefix":"10.14778","volume":"18","author":[{"given":"Yiran","family":"Li","sequence":"first","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong SAR, China"}]},{"given":"Gongyao","family":"Guo","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong SAR, China"}]},{"given":"Chen","family":"Feng","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong SAR, China"}]},{"given":"Jieming","family":"Shi","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong SAR, China"}]}],"member":"320","published-online":{"date-parts":[[2025,9,4]]},"reference":[{"key":"e_1_2_1_1_1","unstructured":"2025. Technical Report. https:\/\/github.com\/CyanideCentral\/AHNEE\/blob\/main\/SAHE_Technical_Report.pdf."},{"key":"e_1_2_1_2_1","volume-title":"Lorenzo Orecchia, and Erasmo Tani.","author":"Ameranis Konstantinos","year":"2024","unstructured":"Konstantinos Ameranis, Adela Frances DePavia, Lorenzo Orecchia, and Erasmo Tani. 2024. Fast Algorithms for Hypergraph PageRank with Applications to Semi-Supervised Learning. In ICML."},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1800683115"},{"key":"e_1_2_1_4_1","unstructured":"Eli Chien Chao Pan Jianhao Peng and Olgica Milenkovic. 2021. You Are AllSet: A Multiset Function Framework for Hypergraph Neural Networks. In ICLR."},{"key":"e_1_2_1_5_1","unstructured":"Uthsav Chitra and Benjamin Raphael. 2019. Random Walks on Hypergraphs with Edge-Dependent Vertex Weights. In ICML. PMLR 1172\u20131181."},{"key":"e_1_2_1_6_1","unstructured":"Matthijs Douze Alexandr Guzhva Chengqi Deng Jeff Johnson Gergely Szilvasy Pierre-Emmanuel Mazar\u00e9 Maria Lomeli Lucas Hosseini and Herv\u00e9 J\u00e9gou. 2024. The Faiss library. (2024). arXiv:2401.08281 [cs.LG]"},{"volume-title":"Self-Supervised Hypergraph Representation Learning","author":"Du Boxin","key":"e_1_2_1_7_1","unstructured":"Boxin Du, Changhe Yuan, Robert Barton, Tal Neiman, and Hanghang Tong. 2022. Self-Supervised Hypergraph Representation Learning. In IEEE Big Data. 505\u2013514."},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12859-021-04197-2"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3709741"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3182052"},{"key":"e_1_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Aditya Grover and Jure Leskovec. 2016. Node2vec: Scalable Feature Learning for Networks. In KDD. 855\u2013864.","DOI":"10.1145\/2939672.2939754"},{"key":"e_1_2_1_12_1","unstructured":"Insu Han Haim Avron and Jinwoo Shin. 2020. Polynomial Tensor Sketch for Element-wise Function of Low-Rank Matrix. In ICML. 3984\u20133993."},{"key":"e_1_2_1_13_1","volume-title":"Search Behavior Prediction: A Hypergraph Perspective. In WSDM (WSDM '23)","author":"Han Yan","year":"2023","unstructured":"Yan Han, Edward W. Huang, Wenqing Zheng, Nikhil Rao, Zhangyang Wang, and Karthik Subbian. 2023. Search Behavior Prediction: A Hypergraph Perspective. In WSDM (WSDM '23). 697\u2013705."},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3388924"},{"key":"e_1_2_1_15_1","doi-asserted-by":"crossref","unstructured":"Jie Huang Chuan Chen Fanghua Ye Jiajing Wu Zibin Zheng and Guohui Ling. 2019. Hyper2vec: Biased Random Walk for Hyper-network Embedding. In DASFAA. 273\u2013277.","DOI":"10.1007\/978-3-030-18590-9_27"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401068"},{"key":"e_1_2_1_17_1","volume-title":"Jaemin Yoo, and Kijung Shin.","author":"Kim Sunwoo","year":"2023","unstructured":"Sunwoo Kim, Shinhwan Kang, Fanchen Bu, Soo Yong Lee, Jaemin Yoo, and Kijung Shin. 2023. HypeBoy: Generative Self-Supervised Representation Learning on Hypergraphs. In ICLR."},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i7.26019"},{"key":"e_1_2_1_19_1","volume-title":"Soo Yong Lee, and Kijung Shin","author":"Lee Geon","year":"2024","unstructured":"Geon Lee, Soo Yong Lee, and Kijung Shin. 2024. VilLain: Self-Supervised Learning on Homogeneous Hypergraphs without Features via Virtual Label Propagation. In WWW. 594\u2013605."},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1137\/S0895479895281484"},{"key":"e_1_2_1_21_1","volume-title":"SHARE: A System for Hierarchical Assistive Recipe Editing. In EMNLP. 11077\u201311090.","author":"Li Shuyang","year":"2022","unstructured":"Shuyang Li, Yufei Li, Jianmo Ni, and Julian McAuley. 2022. SHARE: A System for Hierarchical Assistive Recipe Editing. In EMNLP. 11077\u201311090."},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589261"},{"key":"e_1_2_1_23_1","doi-asserted-by":"crossref","unstructured":"Zhonghang Li Chao Huang Lianghao Xia Yong Xu and Jian Pei. 2022. Spatial-Temporal Hypergraph Self-Supervised Learning for Crime Prediction. In ICDE. 2984\u20132996.","DOI":"10.1109\/ICDE53745.2022.00269"},{"key":"e_1_2_1_24_1","volume-title":"Robust attributed network embedding preserving community information","author":"Liu Yunfei","year":"1874","unstructured":"Yunfei Liu, Zhen Liu, Xiaodong Feng, and Zhongyi Li. 2022. Robust attributed network embedding preserving community information. In ICDE. IEEE, 1874\u2013 1886."},{"volume-title":"Negative sampling for hyperlink prediction in networks","author":"Patil Prasanna","key":"e_1_2_1_25_1","unstructured":"Prasanna Patil, Govind Sharma, and M Narasimha Murty. 2020. Negative sampling for hyperlink prediction in networks. In PAKDD. Springer, 607\u2013619."},{"key":"e_1_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Jiezhong Qiu Laxman Dhulipala Jie Tang Richard Peng and Chi Wang. 2021. LightNE: A Lightweight Graph Processing System for Network Embedding. In SIGMOD. 2281\u20132289.","DOI":"10.1145\/3448016.3457329"},{"key":"e_1_2_1_27_1","doi-asserted-by":"crossref","unstructured":"Jiezhong Qiu Yuxiao Dong Hao Ma Jian Li Kuansan Wang and Jie Tang. 2018. Network Embedding as Matrix Factorization: Unifying DeepWalk LINE PTE and Node2vec. In WSDM. 459\u2013467.","DOI":"10.1145\/3159652.3159706"},{"key":"e_1_2_1_28_1","volume-title":"Hypergraph Clustering Based on PageRank. arXiv:2006.08302 [cs, math] (June","author":"Takai Yuuki","year":"2020","unstructured":"Yuuki Takai, Atsushi Miyauchi, Masahiro Ikeda, and Yuichi Yoshida. 2020. Hypergraph Clustering Based on PageRank. arXiv:2006.08302 [cs, math] (June 2020). arXiv:2006.08302"},{"key":"e_1_2_1_29_1","volume-title":"Collaborative graph neural networks for attributed network embedding. TKDE","author":"Tan Qiaoyu","year":"2023","unstructured":"Qiaoyu Tan, Xin Zhang, Xiao Huang, Hao Chen, Jundong Li, and Xia Hu. 2023. Collaborative graph neural networks for attributed network embedding. TKDE (2023)."},{"key":"e_1_2_1_30_1","first-page":"6","article-title":"FREDE: Anytime Graph Embeddings","volume":"14","author":"Tsitsulin Anton","year":"2021","unstructured":"Anton Tsitsulin, Marina Munkhoeva, Davide Mottin, Panagiotis Karras, Ivan Oseledets, and Emmanuel M\u00fcller. 2021. FREDE: Anytime Graph Embeddings. VLDB 14, 6 (Feb. 2021), 1102\u20131110.","journal-title":"VLDB"},{"key":"e_1_2_1_31_1","volume-title":"Augmentations in Hypergraph Contrastive Learning: Fabricated and Generative. NeurIPS 35 (Dec","author":"Wei Tianxin","year":"2022","unstructured":"Tianxin Wei, Yuning You, Tianlong Chen, Yang Shen, Jingrui He, and Zhangyang Wang. 2022. Augmentations in Hypergraph Contrastive Learning: Fabricated and Generative. NeurIPS 35 (Dec. 2022), 1909\u20131922."},{"key":"e_1_2_1_32_1","doi-asserted-by":"crossref","unstructured":"Anbiao Wu Ye Yuan Changsheng Li Yuliang Ma and Hao Zhang. 2024. Attributed Network Embedding in Streaming Style. In ICDE. 3138\u20133150.","DOI":"10.1109\/ICDE60146.2024.00243"},{"key":"e_1_2_1_33_1","first-page":"2","article-title":"Billion-Scale Bipartite Graph Embedding: A Global-Local Induced Approach","volume":"17","author":"Wu Xueyi","year":"2023","unstructured":"Xueyi Wu, Yuanyuan Xu, Wenjie Zhang, and Ying Zhang. 2023. Billion-Scale Bipartite Graph Embedding: A Global-Local Induced Approach. VLDB 17, 2 (Oct. 2023), 175\u2013183.","journal-title":"VLDB"},{"key":"e_1_2_1_34_1","doi-asserted-by":"crossref","unstructured":"Lianghao Xia Chao Huang and Chuxu Zhang. 2022. Self-Supervised Hypergraph Transformer for Recommender Systems. In KDD. 2100\u20132109.","DOI":"10.1145\/3534678.3539473"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1137\/20M1386062"},{"key":"e_1_2_1_36_1","doi-asserted-by":"crossref","unstructured":"Rongwei Xu Guanfeng Liu Yan Wang Xuyun Zhang Kai Zheng and Xiaofang Zhou. 2024. Adaptive Hypergraph Network for Trust Prediction. In ICDE. 2986\u2013 2999.","DOI":"10.1109\/ICDE60146.2024.00232"},{"key":"e_1_2_1_37_1","volume-title":"Hypergcn: A new method for training graph convolutional networks on hypergraphs. NeurIPS 32","author":"Yadati Naganand","year":"2019","unstructured":"Naganand Yadati, Madhav Nimishakavi, Prateek Yadav, Vikram Nitin, Anand Louis, and Partha Talukdar. 2019. Hypergcn: A new method for training graph convolutional networks on hypergraphs. NeurIPS 32 (2019)."},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i8.28775"},{"key":"e_1_2_1_39_1","first-page":"4","article-title":"LBSN2Vec++: Heterogeneous Hypergraph Embedding for Location-Based Social Networks","volume":"34","author":"Yang Dingqi","year":"2022","unstructured":"Dingqi Yang, Bingqing Qu, Jie Yang, and Philippe Cudr\u00e9-Mauroux. 2022. LBSN2Vec++: Heterogeneous Hypergraph Embedding for Location-Based Social Networks. TKDE 34, 4 (April 2022), 1843\u20131855.","journal-title":"TKDE"},{"key":"e_1_2_1_40_1","first-page":"9","article-title":"Efficient Algorithms for Personalized PageRank Computation: A Survey","volume":"36","author":"Yang Mingji","year":"2024","unstructured":"Mingji Yang, Hanzhi Wang, Zhewei Wei, Sibo Wang, and Ji-Rong Wen. 2024. Efficient Algorithms for Personalized PageRank Computation: A Survey. TKDE 36, 9 (Sept. 2024), 4582\u20134602.","journal-title":"TKDE"},{"key":"e_1_2_1_41_1","first-page":"5","article-title":"Homogeneous Network Embedding for Massive Graphs via Reweighted Personalized PageRank","volume":"13","author":"Yang Renchi","year":"2020","unstructured":"Renchi Yang, Jieming Shi, Xiaokui Xiao, Yin Yang, and Sourav S. Bhowmick. 2020. Homogeneous Network Embedding for Massive Graphs via Reweighted Personalized PageRank. VLDB 13, 5 (Jan. 2020), 670\u2013683.","journal-title":"VLDB"},{"key":"e_1_2_1_42_1","first-page":"6","article-title":"PANE: Scalable and Effective Attributed Network Embedding","volume":"32","author":"Yang Renchi","year":"2023","unstructured":"Renchi Yang, Jieming Shi, Xiaokui Xiao, Yin Yang, Sourav S. Bhowmick, and Juncheng Liu. 2023. PANE: Scalable and Effective Attributed Network Embedding. VLDBJ 32, 6 (Nov. 2023), 1237\u20131262.","journal-title":"VLDBJ"},{"key":"e_1_2_1_43_1","first-page":"1","article-title":"Scaling Attributed Network Embedding to Massive Graphs","volume":"14","author":"Yang Renchi","year":"2020","unstructured":"Renchi Yang, Jieming Shi, Xiaokui Xiao, Yin Yang, Juncheng Liu, and Sourav S. Bhowmick. 2020. Scaling Attributed Network Embedding to Massive Graphs. VLDB 14, 1 (Sept. 2020), 37\u201349.","journal-title":"VLDB"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330860"},{"key":"e_1_2_1_45_1","volume-title":"Modeling Multi-way Relations with Hypergraph Embedding. In CIKM (CIKM '18)","author":"Yu Chia-An","year":"2018","unstructured":"Chia-An Yu, Ching-Lun Tai, Tak-Shing Chan, and Yi-Hsuan Yang. 2018. Modeling Multi-way Relations with Hypergraph Embedding. In CIKM (CIKM '18). 1707\u2013 1710."},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7503.003.0205"},{"key":"e_1_2_1_47_1","first-page":"2","article-title":"Network Representation Learning: From Preprocessing, Feature Extraction to Node Embedding","volume":"55","author":"Zhou Jingya","year":"2022","unstructured":"Jingya Zhou, Ling Liu, Wenqi Wei, and Jianxi Fan. 2022. Network Representation Learning: From Preprocessing, Feature Extraction to Node Embedding. ACM Comput. Surv. 55, 2 (Jan. 2022), 38:1\u201338:35.","journal-title":"ACM Comput. Surv."}],"container-title":["Proceedings of the VLDB Endowment"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.14778\/3749646.3749692","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,5]],"date-time":"2025-09-05T03:29:27Z","timestamp":1757042967000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.14778\/3749646.3749692"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":47,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2025,7]]}},"alternative-id":["10.14778\/3749646.3749692"],"URL":"https:\/\/doi.org\/10.14778\/3749646.3749692","relation":{},"ISSN":["2150-8097"],"issn-type":[{"type":"print","value":"2150-8097"}],"subject":[],"published":{"date-parts":[[2025,7]]},"assertion":[{"value":"2025-09-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}