{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T03:16:05Z","timestamp":1776827765056,"version":"3.51.2"},"reference-count":49,"publisher":"Association for Computing Machinery (ACM)","issue":"3","license":[{"start":{"date-parts":[[2023,2,7]],"date-time":"2023-02-07T00:00:00Z","timestamp":1675728000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Inf. Syst."],"published-print":{"date-parts":[[2023,7,31]]},"abstract":"<jats:p>Sequential recommendation (SR) learns users\u2019 preferences by capturing the sequential patterns from users\u2019 behaviors evolution. As discussed in many works, user\u2013item interactions of SR generally present the intrinsic power-law distribution, which can be ascended to hierarchy-like structures. Previous methods usually handle such hierarchical information by making user\u2013item sectionalization empirically under Euclidean space, which may cause distortion of user\u2013item representation in real online scenarios. In this article, we propose a Poincar\u00e9-based heterogeneous graph neural network named Poincar\u00e9 Heterogeneous Graph Neural Networks for Sequential Recommendation (PHGR) to model the sequential pattern information as well as hierarchical information contained in the data of SR scenarios simultaneously. Specifically, for the purpose of explicitly capturing the hierarchical information, we first construct a weighted user\u2013item heterogeneous graph by aliening all the user\u2013item interactions to improve the perception domain of each user from a global view. Then the output of the global representation would be used to complement the local directed item\u2013item homogeneous graph convolution. By defining a novel hyperbolic inner product operator, the global and local graph representation learning are directly conducted in Poincar\u00e9 ball instead of commonly used projection operation between Poincar\u00e9 ball and Euclidean space, which could alleviate the cumulative error issue of general bidirectional translation process. Moreover, for the purpose of explicitly capturing the sequential dependency information, we design two types of temporal attention operations under Poincar\u00e9 ball space. Empirical evaluations on datasets from the public and financial industry show that PHGR outperforms several comparison methods.<\/jats:p>","DOI":"10.1145\/3568395","type":"journal-article","created":{"date-parts":[[2023,1,11]],"date-time":"2023-01-11T12:05:43Z","timestamp":1673438743000},"page":"1-26","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":24,"title":["Poincar\u00e9 Heterogeneous Graph Neural Networks for Sequential Recommendation"],"prefix":"10.1145","volume":"41","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0144-2148","authenticated-orcid":false,"given":"Naicheng","family":"Guo","sequence":"first","affiliation":[{"name":"Mybank, Ant Group; Department of Computer Science, Shantou University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7082-641X","authenticated-orcid":false,"given":"Xiaolei","family":"Liu","sequence":"additional","affiliation":[{"name":"Mybank, Ant Group, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2949-668X","authenticated-orcid":false,"given":"Shaoshuai","family":"Li","sequence":"additional","affiliation":[{"name":"Mybank, Ant Group, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2465-4941","authenticated-orcid":false,"given":"Qiongxu","family":"Ma","sequence":"additional","affiliation":[{"name":"Mybank, Ant Group, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3728-2294","authenticated-orcid":false,"given":"Kaixin","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Mathematics, Tianjin University, Tianjin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8051-1278","authenticated-orcid":false,"given":"Bing","family":"Han","sequence":"additional","affiliation":[{"name":"Mybank, Ant Group, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1376-075X","authenticated-orcid":false,"given":"Lin","family":"Zheng","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Shantou University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8959-2473","authenticated-orcid":false,"given":"Sheng","family":"Guo","sequence":"additional","affiliation":[{"name":"Mybank, Ant Group, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6817-626X","authenticated-orcid":false,"given":"Xiaobo","family":"Guo","sequence":"additional","affiliation":[{"name":"Mybank, Ant Group, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2023,2,7]]},"reference":[{"key":"e_1_3_2_2_2","article-title":"Multi-relational poincar\u00e9 graph embeddings","volume":"32","author":"Balazevic Ivana","year":"2019","unstructured":"Ivana Balazevic, Carl Allen, and Timothy Hospedales. 2019. Multi-relational poincar\u00e9 graph embeddings. Adv. Neural Inf. Process. Syst. 32 (2019).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2693418"},{"key":"e_1_3_2_4_2","unstructured":"Benjamin Paul Chamberlain James Clough and Marc Peter Deisenroth. 2017. Neural embeddings of graphs in hyperbolic space. arXiv preprint arXiv:1705.10359 (2017)."},{"key":"e_1_3_2_5_2","article-title":"Scalable hyperbolic recommender systems","author":"Chamberlain Benjamin Paul","year":"2019","unstructured":"Benjamin Paul Chamberlain, Stephen R. Hardwick, David R. Wardrope, Fabon Dzogang, Fabio Daolio, and Sa\u00fal Vargas. 2019. Scalable hyperbolic recommender systems. arXiv:1902.08648. Retrieved from https:\/\/arxiv.org\/abs\/1902.08648.","journal-title":"arXiv:1902.08648"},{"key":"e_1_3_2_6_2","article-title":"Low-dimensional hyperbolic knowledge graph embeddings","author":"Chami Ines","year":"2020","unstructured":"Ines Chami, Adva Wolf, Da-Cheng Juan, Frederic Sala, Sujith Ravi, and Christopher R\u00e9. 2020. Low-dimensional hyperbolic knowledge graph embeddings. arXiv:2005.00545. Retrieved from https:\/\/arxiv.org\/abs\/2005.00545.","journal-title":"arXiv:2005.00545"},{"key":"e_1_3_2_7_2","first-page":"4868","article-title":"Hyperbolic graph convolutional neural networks","volume":"32","author":"Chami Ines","year":"2019","unstructured":"Ines Chami, Zhitao Ying, Christopher R\u00e9, and Jure Leskovec. 2019. Hyperbolic graph convolutional neural networks. Adv. Neural Inf. Process. Syst. 32 (2019), 4868\u20134879.","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403170"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449974"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2018.2881260"},{"key":"e_1_3_2_11_2","first-page":"324","volume-title":"Joint IAPR International Workshops on Statistical Techniques in Pattern Recognition (SPR) and Structural and Syntactic Pattern Recognition (SSPR)","author":"Duin Robert P. W.","year":"2010","unstructured":"Robert P. W. Duin and El\u017cbieta P\u0119kalska. 2010. Non-euclidean dissimilarities: Causes and informativeness. In Joint IAPR International Workshops on Statistical Techniques in Pattern Recognition (SPR) and Structural and Syntactic Pattern Recognition (SSPR). Springer, 324\u2013333."},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462978"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401049"},{"key":"e_1_3_2_14_2","article-title":"Hyperbolic neural networks","author":"Ganea Octavian-Eugen","year":"2018","unstructured":"Octavian-Eugen Ganea, Gary B\u00e9cigneul, and Thomas Hofmann. 2018. Hyperbolic neural networks. arXiv:1805.09112. Retrieved from https:\/\/arxiv.org\/abs\/1805.09112.","journal-title":"arXiv:1805.09112"},{"key":"e_1_3_2_15_2","article-title":"Hyperbolic attention networks","author":"Gulcehre Caglar","year":"2018","unstructured":"Caglar Gulcehre, Misha Denil, Mateusz Malinowski, Ali Razavi, Razvan Pascanu, Karl Moritz Hermann, Peter Battaglia, Victor Bapst, David Raposo, Adam Santoro, et\u00a0al. 2018. Hyperbolic attention networks. arXiv:1805.09786. Retrieved from https:\/\/arxiv.org\/abs\/1805.09786.","journal-title":"arXiv:1805.09786"},{"key":"e_1_3_2_16_2","article-title":"HCGR: Hyperbolic contrastive graph representation learning for session-based recommendation","author":"Guo Naicheng","year":"2021","unstructured":"Naicheng Guo, Xiaolei Liu, Shaoshuai Li, Qiongxu Ma, Yunan Zhao, Bing Han, Lin Zheng, Kaixin Gao, and Xiaobo Guo. 2021. HCGR: Hyperbolic contrastive graph representation learning for session-based recommendation. arXiv:2107.05366. Retrieved from https:\/\/arxiv.org\/abs\/2107.05366.","journal-title":"arXiv:2107.05366"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2016.0030"},{"key":"e_1_3_2_18_2","article-title":"Session-based recommendations with recurrent neural networks","author":"Hidasi Bal\u00e1zs","year":"2015","unstructured":"Bal\u00e1zs Hidasi, Alexandros Karatzoglou, Linas Baltrunas, and Domonkos Tikk. 2015. Session-based recommendations with recurrent neural networks. arXiv:1511.06939. Retrieved from https:\/\/arxiv.org\/abs\/1511.06939.","journal-title":"arXiv:1511.06939"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2018.00035"},{"key":"e_1_3_2_20_2","volume-title":"Efficient Navigation in Scale-free Networks Embedded in Hyperbolic Metric Spaces","author":"Krioukov Dmitri","year":"2008","unstructured":"Dmitri Krioukov, Fragkiskos Papadopoulos, Mari\u00e1n Bogun\u00e1, Amin Vahdat, et\u00a0al. 2008. Efficient Navigation in Scale-free Networks Embedded in Hyperbolic Metric Spaces. Technical Report."},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.82.036106"},{"key":"e_1_3_2_22_2","article-title":"HSR: Hyperbolic social recommender","author":"Li Anchen","year":"2021","unstructured":"Anchen Li and Bo Yang. 2021. HSR: Hyperbolic social recommender. arXiv:2102.09389. Retrieved from https:\/\/arxiv.org\/abs\/2102.09389.","journal-title":"arXiv:2102.09389"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3132847.3132926"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401080"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3383313.3412247"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330984"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5945"},{"key":"e_1_3_2_28_2","first-page":"4285","volume-title":"Proceedings of the 35th AAAI Conference on Artificial Intelligence (AAAI\u201921), the 33rd Conference on Innovative Applications of Artificial Intelligence (IAAI\u201921), and the 11th Symposium on Educational Advances in Artificial Intelligence (EAAI\u201921)","author":"Ma Chen","year":"2021","unstructured":"Chen Ma, Liheng Ma, Yingxue Zhang, Haolun Wu, Xue Liu, and Mark Coates. 2021. Knowledge-enhanced top-K recommendation in poincar\u00e9 ball. In Proceedings of the 35th AAAI Conference on Artificial Intelligence (AAAI\u201921), the 33rd Conference on Innovative Applications of Artificial Intelligence (IAAI\u201921), and the 11th Symposium on Educational Advances in Artificial Intelligence (EAAI\u201921). 4285\u20134293."},{"key":"e_1_3_2_29_2","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. Advances in Neural Information Processing Systems 32 (2019)."},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3383313.3412219"},{"key":"e_1_3_2_31_2","first-page":"6338","article-title":"Poincar\u00e9 embeddings for learning hierarchical representations","volume":"30","author":"Nickel Maximillian","year":"2017","unstructured":"Maximillian Nickel and Douwe Kiela. 2017. Poincar\u00e9 embeddings for learning hierarchical representations. Adv. Neural Inf. Process. Syst. 30 (2017), 6338\u20136347.","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"e_1_3_2_32_2","article-title":"Poincar\u00e9 wasserstein autoencoder","author":"Ovinnikov Ivan","year":"2019","unstructured":"Ivan Ovinnikov. 2019. Poincar\u00e9 wasserstein autoencoder. arXiv:1901.01427. Retrieved from https:\/\/arxiv.org\/abs\/1901.01427.","journal-title":"arXiv:1901.01427"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.67.026112"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772773"},{"key":"e_1_3_2_35_2","first-page":"4460","volume-title":"International Conference on Machine Learning","author":"Sala Frederic","year":"2018","unstructured":"Frederic Sala, Chris De Sa, Albert Gu, and Christopher R\u00e9. 2018. Representation tradeoffs for hyperbolic embeddings. In International Conference on Machine Learning. PMLR, 4460\u20134469."},{"key":"e_1_3_2_36_2","article-title":"Multi-manifold learning for large-scale targeted advertising system","author":"Shin Kyuyong","year":"2020","unstructured":"Kyuyong Shin, Young-Jin Park, Kyung-Min Kim, and Sunyoung Kwon. 2020. Multi-manifold learning for large-scale targeted advertising system. arXiv: 2007.02334. Retrieved from https:\/\/arxiv.org\/abs\/2007.02334.","journal-title":"arXiv: 2007.02334"},{"key":"e_1_3_2_37_2","article-title":"Mixed-curvature variational autoencoders","author":"Skopek Ondrej","year":"2019","unstructured":"Ondrej Skopek, Octavian-Eugen Ganea, and Gary B\u00e9cigneul. 2019. Mixed-curvature variational autoencoders. arXiv:1911.08411. Retrieved from https:\/\/arxiv.org\/abs\/1911.08411.","journal-title":"arXiv:1911.08411"},{"key":"e_1_3_2_38_2","article-title":"Poincar\u00e9 glove: Hyperbolic word embeddings","author":"Tifrea Alexandru","year":"2018","unstructured":"Alexandru Tifrea, Gary B\u00e9cigneul, and Octavian-Eugen Ganea. 2018. Poincar\u00e9 glove: Hyperbolic word embeddings. arXiv:1810.06546. Retrieved from https:\/\/arxiv.org\/abs\/1810.06546.","journal-title":"arXiv:1810.06546"},{"key":"e_1_3_2_39_2","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N. Gomez Lukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. Advances in Neural Information Processing Systems 30 (2017)."},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.3390\/info11080388"},{"key":"e_1_3_2_41_2","doi-asserted-by":"crossref","unstructured":"Hao Wang Defu Lian Hanghang Tong Qi Liu Zhenya Huang and Ennhong Chen. 2021. Hypersorec: Exploiting hyperbolic user and item representations with multiple aspects for social-aware recommendation. ACM Transactions on Information Systems (TOIS) 40 2 (2021) 1\u201328.","DOI":"10.1145\/3463913"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/2766462.2767694"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2018.2789443"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401142"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301346"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533533"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/547"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/3298689.3346996"},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330961"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401330"}],"container-title":["ACM Transactions on Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3568395","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3568395","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:51:33Z","timestamp":1750182693000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3568395"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,7]]},"references-count":49,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2023,7,31]]}},"alternative-id":["10.1145\/3568395"],"URL":"https:\/\/doi.org\/10.1145\/3568395","relation":{},"ISSN":["1046-8188","1558-2868"],"issn-type":[{"value":"1046-8188","type":"print"},{"value":"1558-2868","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,7]]},"assertion":[{"value":"2021-12-31","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-07-06","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-02-07","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}