{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T17:30:05Z","timestamp":1770744605831,"version":"3.49.0"},"reference-count":61,"publisher":"Association for Computing Machinery (ACM)","issue":"2","funder":[{"name":"FAIR","award":["PE0000013"],"award-info":[{"award-number":["PE0000013"]}]},{"name":"MUR National Recovery and Resilience Plan funded by the European Union - NextGenerationEU"},{"name":"Italian Ministry of Education and Research","award":["2022AEFHAZ"],"award-info":[{"award-number":["2022AEFHAZ"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Recomm. Syst."],"published-print":{"date-parts":[[2026,6,30]]},"abstract":"<jats:p>\n                    Recent advancements in Graph Neural Networks (GNN) have facilitated their widespread adoption in various applications, including recommendation systems. GNNs have proven to be effective in addressing the challenges posed by recommendation systems by efficiently modeling graphs in which nodes represent users or items and edges denote preference relationships. However, current GNN techniques represent nodes by means of a single static vector, which may inadequately capture the intricate complexities of users and items. To overcome these limitations, we propose a solution integrating a cutting-edge model inspired by category theory: Sheaf4Rec. Unlike single vector representations, Sheaf Neural Networks and their corresponding Laplacians represent each node (and edge) using a vector space. Our approach takes advantage of this theory and results in a more comprehensive representation that can be effectively exploited during inference, providing a versatile method applicable to a wide range of graph-related tasks and demonstrating unparalleled performance. Our proposed model exhibits a noteworthy relative improvement of up to 8.53% on F1-Score@10 and an impressive increase of up to 11.29% on NDCG@10, outperforming existing state-of-the-art models such as Neural Graph Collaborative Filtering (NGCF), KGTORe and other recently developed GNN-based models. In addition to its superior predictive capabilities, Sheaf4Rec shows remarkable improvements in terms of efficiency: we observe substantial runtime improvements ranging from 2.5% up to 37% when compared to other GNN-based competitor models, indicating a more efficient way of handling information while achieving better performance. Code is available at\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/github.com\/antoniopurificato\/Sheaf4Rec\">https:\/\/github.com\/antoniopurificato\/Sheaf4Rec<\/jats:ext-link>\n                    .\n                  <\/jats:p>","DOI":"10.1145\/3742898","type":"journal-article","created":{"date-parts":[[2025,6,4]],"date-time":"2025-06-04T07:34:26Z","timestamp":1749022466000},"page":"1-26","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Sheaf4Rec: Sheaf Neural Networks for Graph-based Recommender Systems"],"prefix":"10.1145","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-3933-380X","authenticated-orcid":false,"given":"Antonio","family":"Purificato","sequence":"first","affiliation":[{"name":"Department of computer, control and management engineering Antonio Ruberti, Universita degli Studi di Roma La Sapienza and Amazon","place":["Rome, Italy"]},{"name":"Eu Intech, Amazon Europe Core S\u00e0rl","place":["Rome, Italy"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2596-7452","authenticated-orcid":false,"given":"Giulia","family":"Cassar\u00e0","sequence":"additional","affiliation":[{"name":"Department of computer, control and management engineering Antonio Ruberti, Universita degli Studi di Roma La Sapienza and Amazon","place":["Rome, Italy"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1339-6983","authenticated-orcid":false,"given":"Federico","family":"Siciliano","sequence":"additional","affiliation":[{"name":"Department of computer, control and management engineering Antonio Ruberti, Universita degli Studi di Roma La Sapienza and Amazon","place":["Rome, Italy"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0540-5053","authenticated-orcid":false,"given":"Pietro","family":"Li\u00f2","sequence":"additional","affiliation":[{"name":"Computer Science and Technology, University of Cambridge","place":["Cambridge, United Kingdom of Great Britain and Northern Ireland"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7669-9055","authenticated-orcid":false,"given":"Fabrizio","family":"Silvestri","sequence":"additional","affiliation":[{"name":"Department of computer, control and management engineering Antonio Ruberti, Universita degli Studi di Roma La Sapienza and Amazon","place":["Rome, Italy"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,11,22]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/MIC.2003.1167344"},{"key":"e_1_3_2_3_2","unstructured":"Uri Alon and Eran Yahav. 2021. On the bottleneck of Graph Neural Networks and its Practical Implications. In International Conference on Learning Representations."},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3604915.3610643"},{"key":"e_1_3_2_5_2","first-page":"28","volume-title":"Proceedings of the Topological, Algebraic and Geometric Learning Workshops 2022","author":"Barbero Federico","year":"2022","unstructured":"Federico Barbero, Cristian Bodnar, Haitz S\u00e1ez de Oc\u00e1riz Borde, Michael Bronstein, Petar Veli\u010dkovi\u0107, and Pietro Li\u00f2. 2022. Sheaf neural networks with connection laplacians. In Proceedings of the Topological, Algebraic and Geometric Learning Workshops 2022. PMLR, 28\u201336."},{"key":"e_1_3_2_6_2","article-title":"A reproducible analysis of sequential recommender systems","author":"Betello Filippo","year":"2024","unstructured":"Filippo Betello, Antonio Purificato, Federico Siciliano, Giovanni Trappolini, Andrea Bacciu, Nicola Tonellotto, and Fabrizio Silvestri. 2024. A reproducible analysis of sequential recommender systems. IEEE Access (2024).","journal-title":"IEEE Access"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-56060-6_14"},{"key":"e_1_3_2_8_2","first-page":"18527","article-title":"Neural sheaf diffusion: A topological perspective on heterophily and oversmoothing in gnns","volume":"35","author":"Bodnar Cristian","year":"2022","unstructured":"Cristian Bodnar, Francesco Di Giovanni, Benjamin Chamberlain, Pietro Lio, and Michael Bronstein. 2022. Neural sheaf diffusion: A topological perspective on heterophily and oversmoothing in gnns. Advances in Neural Information Processing Systems 35 (2022), 18527\u201318541.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2015.04.237"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/1921591.1921593"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3030693"},{"key":"e_1_3_2_12_2","first-page":"12087","article-title":"Sheaf hypergraph networks","volume":"36","author":"Duta Iulia","year":"2023","unstructured":"Iulia Duta, Giulia Cassar\u00e0, Fabrizio Silvestri, and Pietro Li\u00f2. 2023. Sheaf hypergraph networks. Advances in Neural Information Processing Systems 36 (2023), 12087\u201312099.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.5555\/2969442.2969488"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3588901"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.21136\/CMJ.1973.101168"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3568022"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1007\/s41468-019-00038-7"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1137\/20M1341088"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591647"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401063"},{"key":"e_1_3_2_21_2","doi-asserted-by":"crossref","unstructured":"Xiangnan He Lizi Liao Hanwang Zhang Liqiang Nie Xia Hu and Tat-Seng Chua. 2017. Neural collaborative filtering. In Proceedings of the 26th International Conference on World Wide Web. 173\u2013182.","DOI":"10.1145\/3038912.3052569"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/358916.358995"},{"key":"e_1_3_2_23_2","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 (2015)."},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599768"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2018.00035"},{"key":"e_1_3_2_26_2","unstructured":"Thomas N. Kipf and Max Welling. 2017. Semi-supervised classification with graph convolutional networks. In International Conference on Learning Representations."},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2009.263"},{"key":"e_1_3_2_28_2","unstructured":"Oleksii Kuchaiev and Boris Ginsburg. 2017. Training deep autoencoders for collaborative filtering. arXiv:1708.01715. Retrieved from https:\/\/arxiv.org\/abs\/1708.01715 (2017)."},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1038\/44565"},{"key":"e_1_3_2_30_2","unstructured":"Guohao Li Matthias Muller Ali Thabet and Bernard Ghanem. 2019. DeepGCNs: Can GCNs go as deep as CNNs? In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 9267\u20139276."},{"key":"e_1_3_2_31_2","doi-asserted-by":"crossref","unstructured":"Dawen Liang Laurent Charlin James McInerney and David M. Blei. 2016. Modeling user exposure in recommendation. In Proceedings of the 25th International Conference on World Wide Web. 951\u2013961.","DOI":"10.1145\/2872427.2883090"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/MIC.2003.1167344"},{"key":"e_1_3_2_33_2","article-title":"Learning disentangled representations for recommendation","volume":"32","author":"Ma Jianxin","year":"2019","unstructured":"Jianxin Ma, Chang Zhou, Peng Cui, Hongxia Yang, and Wenwu Zhu. 2019. Learning disentangled representations for recommendation. Advances in Neural Information Processing Systems 32 (2019).","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_34_2","volume-title":"Sheaves in Geometry and Logic: A First Introduction to Topos Theory","author":"MacLane Saunders","year":"2012","unstructured":"Saunders MacLane and Ieke Moerdijk. 2012. Sheaves in Geometry and Logic: A First Introduction to Topos Theory. Springer Science & Business Media."},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/3604915.3608804"},{"key":"e_1_3_2_36_2","doi-asserted-by":"crossref","unstructured":"K. Mao J. Zhu X. Xiao B. Lu Z. Wang and X. UltraGCN He. 2023. Ultra simplification of graph convolutional networks for recommendation. In Proceedings of the 30th ACM International Conference on Information & Knowledge Management. 1253\u20131262.","DOI":"10.1145\/3459637.3482291"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1159"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/2766462.2767755"},{"key":"e_1_3_2_39_2","unstructured":"Kenta Oono and Taiji Suzuki. 2019. Graph neuralnetworks exponentially lose expressive power for node classification. In International Conference on Learning Representations."},{"key":"e_1_3_2_40_2","first-page":"111","volume-title":"Proceedings of the International Workshop on Recommender Systems for Sustainability and Social Good","author":"Purificato Antonio","year":"2024","unstructured":"Antonio Purificato and Fabrizio Silvestri. 2024. Eco-aware graph neural networks for sustainable recommendations. In Proceedings of the International Workshop on Recommender Systems for Sustainability and Social Good. Springer, 111\u2013122."},{"key":"e_1_3_2_41_2","unstructured":"Steffen Rendle Christoph Freudenthaler Zeno Gantner and Lars Schmidt-Thieme. 2012. BPR: Bayesian Personalized Ranking from Implicit Feedback. arXiv:1205.2618. Retrieved from DOI:https:\/\/arxiv.org\/abs\/1205.2618"},{"key":"e_1_3_2_42_2","doi-asserted-by":"crossref","unstructured":"Noveen Sachdeva Giuseppe Manco Ettore Ritacco and Vikram Pudi. 2019. Sequential variational autoencoders for collaborative filtering. In Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining. 600\u2013608.","DOI":"10.1145\/3289600.3291007"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3450120"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/371920.372071"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3680069"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005605"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/2740908.2742726"},{"key":"e_1_3_2_48_2","volume-title":"A Cellular Description of the Derived Category of a Stratified Space","author":"Shepard A. D.","year":"1985","unstructured":"A. D. Shepard. 1985. A Cellular Description of the Derived Category of a Stratified Space. Brown University. Retrieved from https:\/\/books.google.it\/books?id=0qbyGwAACAAJ"},{"key":"e_1_3_2_49_2","unstructured":"Rianne van den Berg Thomas N. Kipf and Max Welling. 2017. Graph Convolutional Matrix Completion. arXiv:1706.02263. Retrieved from https:\/\/arxiv.org\/abs\/1706.02263"},{"key":"e_1_3_2_50_2","unstructured":"Petar Veli\u010dkovi\u0107 Guillem Cucurull Arantxa Casanova Adriana Romero Pietro Li\u00f2 and Yoshua Bengio. 2018. Graph attention networks. In International Conference on Learning Representations."},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","unstructured":"Hongwei Wang Fuzheng Zhang Jialin Wang Miao Zhao Wenjie Li Xing Xie and Minyi Guo. 2018. RippleNet. In Proceedings of the 27th ACM International Conference on Information and Knowledge Management.DOI:DOI:10.1145\/3269206.3271739","DOI":"10.1145\/3269206.3271739"},{"key":"e_1_3_2_52_2","doi-asserted-by":"crossref","unstructured":"Xiang Wang Xiangnan He Meng Wang Fuli Feng and Tat-Seng Chua. 2019. Neural graph collaborative filtering. In Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval. 165\u2013174.","DOI":"10.1145\/3331184.3331267"},{"key":"e_1_3_2_53_2","unstructured":"Eric W. Weisstein. 2004. Bonferroni correction. Retrieved from https:\/\/mathworld.wolfram.com\/ (2004)."},{"key":"e_1_3_2_54_2","volume-title":"Introduction to Graph Theory","author":"West. Douglas Brent","year":"2001","unstructured":"Douglas Brent West.2001. Introduction to Graph Theory. Vol. 2. Prentice hall Upper Saddle River."},{"key":"e_1_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/3535101"},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"e_1_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2605085"},{"key":"e_1_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/592"},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1145\/3285029"},{"key":"e_1_3_2_60_2","unstructured":"Qingqing Zhao David B. Lindell and Gordon Wetzstein. 2022. Learning to solve PDE-constrained inverse problems with graph networks. In International Conference on Machine Learning. PMLR 26895\u201326910."},{"key":"e_1_3_2_61_2","doi-asserted-by":"publisher","unstructured":"Xun Zhou Jing He Guangyan Huang and Yanchun Zhang. 2015. SVD-based incremental approaches for recommender systems. Journal of Computer and System Sciences 4 (2015) 717\u2013733. DOI:DOI:10.1016\/j.jcss.2014.11.016","DOI":"10.1016\/j.jcss.2014.11.016"},{"key":"e_1_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2017.03.009"}],"container-title":["ACM Transactions on Recommender Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3742898","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T16:50:56Z","timestamp":1763830256000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3742898"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,22]]},"references-count":61,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,6,30]]}},"alternative-id":["10.1145\/3742898"],"URL":"https:\/\/doi.org\/10.1145\/3742898","relation":{},"ISSN":["2770-6699"],"issn-type":[{"value":"2770-6699","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,22]]},"assertion":[{"value":"2024-11-21","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-05-30","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-11-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}