{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T01:11:31Z","timestamp":1774487491997,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":52,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,9,14]],"date-time":"2023-09-14T00:00:00Z","timestamp":1694649600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"CityU - HKIDS Early Career Research Grant","award":["No.9360163"],"award-info":[{"award-number":["No.9360163"]}]},{"name":"SIRG - CityU Strategic Interdisciplinary Research Grant","award":["No.7020046, No.7020074"],"award-info":[{"award-number":["No.7020046, No.7020074"]}]},{"name":"Huawei (Huawei Innovation Research Program)"},{"name":"APRC - CityU New Research Initiatives","award":["No.9610565"],"award-info":[{"award-number":["No.9610565"]}]},{"name":"Tencent (CCF-Tencent Open Fund)"},{"name":"Tencent (Tencent Rhino-Bird Focused Research Program)"},{"name":"Ant Group (Ant Group Research Fund)"},{"name":"Ant Group (CCF-Ant Research Fund)"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,9,14]]},"DOI":"10.1145\/3604915.3608779","type":"proceedings-article","created":{"date-parts":[[2023,9,14]],"date-time":"2023-09-14T22:40:23Z","timestamp":1694731223000},"page":"101-111","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":34,"title":["STRec: Sparse Transformer for Sequential Recommendations"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-7754-9783","authenticated-orcid":false,"given":"Chengxi","family":"Li","sequence":"first","affiliation":[{"name":"City University of Hong Kong, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2852-9910","authenticated-orcid":false,"given":"Yejing","family":"Wang","sequence":"additional","affiliation":[{"name":"City University of Hong Kong, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0751-2602","authenticated-orcid":false,"given":"Qidong","family":"Liu","sequence":"additional","affiliation":[{"name":"The Faculty of Electronic Information, Xi'an Jiaotong University, City University of Hong Kong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2926-4416","authenticated-orcid":false,"given":"Xiangyu","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Data Science, City University of Hong Kong, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5976-0707","authenticated-orcid":false,"given":"Wanyu","family":"Wang","sequence":"additional","affiliation":[{"name":"City University of Hong Kong, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9594-1919","authenticated-orcid":false,"given":"Yiqi","family":"Wang","sequence":"additional","affiliation":[{"name":"Michigan State University, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6755-871X","authenticated-orcid":false,"given":"Lixin","family":"Zou","sequence":"additional","affiliation":[{"name":"Wuhan University, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4049-1233","authenticated-orcid":false,"given":"Wenqi","family":"Fan","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3370-471X","authenticated-orcid":false,"given":"Qing","family":"Li","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, China"}]}],"member":"320","published-online":{"date-parts":[[2023,9,14]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Longformer: The long-document transformer. arXiv preprint arXiv:2004.05150","author":"Beltagy Iz","year":"2020","unstructured":"Iz Beltagy, Matthew\u00a0E Peters, and Arman Cohan. 2020. Longformer: The long-document transformer. arXiv preprint arXiv:2004.05150 (2020)."},{"key":"e_1_3_2_1_2_1","volume-title":"Generating long sequences with sparse transformers. arXiv preprint arXiv:1904.10509","author":"Child Rewon","year":"2019","unstructured":"Rewon Child, Scott Gray, Alec Radford, and Ilya Sutskever. 2019. Generating long sequences with sparse transformers. arXiv preprint arXiv:1904.10509 (2019)."},{"key":"e_1_3_2_1_3_1","volume-title":"Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078","author":"Cho Kyunghyun","year":"2014","unstructured":"Kyunghyun Cho, Bart Van\u00a0Merri\u00ebnboer, Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio. 2014. Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078 (2014)."},{"key":"e_1_3_2_1_4_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_5_1","unstructured":"Emil\u00a0Julius Gumbel. 1954. Statistical theory of extreme values and some practical applications: a series of lectures. Vol.\u00a033. US Government Printing Office."},{"key":"e_1_3_2_1_6_1","unstructured":"Huifeng Guo Ruiming Tang Yunming Ye Zhenguo Li and Xiuqiang He. 2017. DeepFM: a factorization-machine based neural network for CTR prediction. arXiv preprint arXiv:1703.04247 (2017)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2016.0030"},{"key":"e_1_3_2_1_8_1","volume-title":"Session-based recommendations with recurrent neural networks. arXiv preprint arXiv:1511.06939","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 preprint arXiv:1511.06939 (2015)."},{"key":"e_1_3_2_1_9_1","volume-title":"International Conference on Machine Learning. PMLR, 9099\u20139117","author":"Hua Weizhe","year":"2022","unstructured":"Weizhe Hua, Zihang Dai, Hanxiao Liu, and Quoc Le. 2022. Transformer quality in linear time. In International Conference on Machine Learning. PMLR, 9099\u20139117."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2505515.2505665"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2018.00035"},{"key":"e_1_3_2_1_12_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma P","year":"2014","unstructured":"Diederik\u00a0P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_13_1","volume-title":"Reformer: The efficient transformer. arXiv preprint arXiv:2001.04451","author":"Kitaev Nikita","year":"2020","unstructured":"Nikita Kitaev, \u0141ukasz Kaiser, and Anselm Levskaya. 2020. Reformer: The efficient transformer. arXiv preprint arXiv:2001.04451 (2020)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2009.263"},{"key":"e_1_3_2_1_15_1","volume-title":"Learning the parts of objects by non-negative matrix factorization. Nature 401, 6755","author":"Lee D","year":"1999","unstructured":"Daniel\u00a0D Lee and H\u00a0Sebastian Seung. 1999. Learning the parts of objects by non-negative matrix factorization. Nature 401, 6755 (1999), 788\u2013791."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371786"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3132847.3132926"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583440"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/297"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583378"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539204"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-023-01839-0"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3298689.3347000"},{"key":"e_1_3_2_1_24_1","volume-title":"Random feature attention. arXiv preprint arXiv:2103.02143","author":"Peng Hao","year":"2021","unstructured":"Hao Peng, Nikolaos Pappas, Dani Yogatama, Roy Schwartz, Noah\u00a0A Smith, and Lingpeng Kong. 2021. Random feature attention. arXiv preprint arXiv:2103.02143 (2021)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330666"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412744"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401440"},{"key":"e_1_3_2_1_28_1","volume-title":"Dynamicvit: Efficient vision transformers with dynamic token sparsification. Advances in neural information processing systems 34","author":"Rao Yongming","year":"2021","unstructured":"Yongming Rao, Wenliang Zhao, Benlin Liu, Jiwen Lu, Jie Zhou, and Cho-Jui Hsieh. 2021. Dynamicvit: Efficient vision transformers with dynamic token sparsification. Advances in neural information processing systems 34 (2021), 13937\u201313949."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2010.127"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772773"},{"key":"e_1_3_2_1_31_1","volume-title":"Is attention interpretable?arXiv preprint arXiv:1906.03731","author":"Serrano Sofia","year":"2019","unstructured":"Sofia Serrano and Noah\u00a0A Smith. 2019. Is attention interpretable?arXiv preprint arXiv:1906.03731 (2019)."},{"key":"e_1_3_2_1_32_1","volume-title":"An MDP-based recommender system.Journal of Machine Learning Research 6, 9","author":"Shani Guy","year":"2005","unstructured":"Guy Shani, David Heckerman, Ronen\u00a0I Brafman, and Craig Boutilier. 2005. An MDP-based recommender system.Journal of Machine Learning Research 6, 9 (2005)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357895"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/2988450.2988452"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3530811"},{"key":"e_1_3_2_1_36_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan\u00a0N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_37_1","volume-title":"Linformer: Self-attention with linear complexity. arXiv preprint arXiv:2006.04768","author":"Wang Sinong","year":"2020","unstructured":"Sinong Wang, Belinda\u00a0Z Li, Madian Khabsa, Han Fang, and Hao Ma. 2020. Linformer: Self-attention with linear complexity. arXiv preprint arXiv:2006.04768 (2020)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512071"},{"key":"e_1_3_2_1_39_1","first-page":"22419","article-title":"Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting","volume":"34","author":"Wu Haixu","year":"2021","unstructured":"Haixu Wu, Jiehui Xu, Jianmin Wang, and Mingsheng Long. 2021. Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting. Advances in Neural Information Processing Systems 34 (2021), 22419\u201322430.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3511936"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583361"},{"key":"e_1_3_2_1_42_1","first-page":"17283","article-title":"Big bird: Transformers for longer sequences","volume":"33","author":"Zaheer Manzil","year":"2020","unstructured":"Manzil Zaheer, Guru Guruganesh, Kumar\u00a0Avinava Dubey, Joshua Ainslie, Chris Alberti, Santiago Ontanon, Philip Pham, Anirudh Ravula, Qifan Wang, Li Yang, 2020. Big bird: Transformers for longer sequences. Advances in Neural Information Processing Systems 33 (2020), 17283\u201317297.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583513"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557348"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"crossref","unstructured":"Tingting Zhang Pengpeng Zhao Yanchi Liu Victor\u00a0S Sheng Jiajie Xu Deqing Wang Guanfeng Liu and Xiaofang Zhou. 2019. Feature-level Deeper Self-Attention Network for Sequential Recommendation.. In IJCAI. 4320\u20134326.","DOI":"10.24963\/ijcai.2019\/600"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557461"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482016"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449962"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3511020","article-title":"Interaction-aware drug package recommendation via policy gradient","volume":"41","author":"Zheng Zhi","year":"2023","unstructured":"Zhi Zheng, Chao Wang, Tong Xu, Dazhong Shen, Penggang Qin, Xiangyu Zhao, Baoxing Huai, Xian Wu, and Enhong Chen. 2023. Interaction-aware drug package recommendation via policy gradient. ACM Transactions on Information Systems 41, 1 (2023), 1\u201332.","journal-title":"ACM Transactions on Information Systems"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015941"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17325"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3411954"}],"event":{"name":"RecSys '23: Seventeenth ACM Conference on Recommender Systems","location":"Singapore Singapore","acronym":"RecSys '23","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGAI ACM Special Interest Group on Artificial Intelligence","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGIR ACM Special Interest Group on Information Retrieval","SIGCHI ACM Special Interest Group on Computer-Human Interaction","SIGecom Special Interest Group on Economics and Computation"]},"container-title":["Proceedings of the 17th ACM Conference on Recommender Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3604915.3608779","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3604915.3608779","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:46:06Z","timestamp":1750178766000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3604915.3608779"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,14]]},"references-count":52,"alternative-id":["10.1145\/3604915.3608779","10.1145\/3604915"],"URL":"https:\/\/doi.org\/10.1145\/3604915.3608779","relation":{},"subject":[],"published":{"date-parts":[[2023,9,14]]},"assertion":[{"value":"2023-09-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}