{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T10:20:47Z","timestamp":1778149247609,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":65,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8,3]]},"DOI":"10.1145\/3711896.3737108","type":"proceedings-article","created":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T13:30:13Z","timestamp":1754055013000},"page":"1094-1105","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Revisiting Self-attention for Cross-domain Sequential Recommendation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-9054-3856","authenticated-orcid":false,"given":"Clark Mingxuan","family":"Ju","sequence":"first","affiliation":[{"name":"Snap Inc., Bellevue, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9539-5100","authenticated-orcid":false,"given":"Leonardo","family":"Neves","sequence":"additional","affiliation":[{"name":"Snap Inc., Santa Monica, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1840-8618","authenticated-orcid":false,"given":"Bhuvesh","family":"Kumar","sequence":"additional","affiliation":[{"name":"Snap Inc., Bellevue, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3139-3339","authenticated-orcid":false,"given":"Liam","family":"Collins","sequence":"additional","affiliation":[{"name":"Snap Inc., Bellevue, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7660-1732","authenticated-orcid":false,"given":"Tong","family":"Zhao","sequence":"additional","affiliation":[{"name":"Snap Inc., Bellevue, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5310-1547","authenticated-orcid":false,"given":"Yuwei","family":"Qiu","sequence":"additional","affiliation":[{"name":"Snap Inc., Palo Alto, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0434-9194","authenticated-orcid":false,"given":"Qing","family":"Dou","sequence":"additional","affiliation":[{"name":"Snap Inc., Palo Alto, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9881-5640","authenticated-orcid":false,"given":"Sohail","family":"Nizam","sequence":"additional","affiliation":[{"name":"Snap Inc., Santa Monica, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1472-5537","authenticated-orcid":false,"given":"Sen","family":"Yang","sequence":"additional","affiliation":[{"name":"Snap Inc., Santa Monica, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3261-8430","authenticated-orcid":false,"given":"Neil","family":"Shah","sequence":"additional","affiliation":[{"name":"Snap Inc., Bellevue, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,8,3]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Longformer: The long-document transformer. arXiv preprint arXiv:2004.05150(2020).","author":"Beltagy Iz","year":"2020","unstructured":"Iz Beltagy, Matthew E Peters, and Arman Cohan. 2020. Longformer: The long-document transformer. arXiv preprint arXiv:2004.05150(2020)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557262"},{"key":"e_1_3_2_1_3_1","unstructured":"Junyoung Chung Caglar Gulcehre KyungHyun Cho and Yoshua Bengio. 2014. Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555(2014)."},{"key":"e_1_3_2_1_4_1","unstructured":"Zeyu Cui Jianxin Ma Chang Zhou Jingren Zhou and Hongxia Yang. 2022. M6-rec: Generative pretrained language models are open-ended recommender systems. arXiv preprint arXiv:2205.08084(2022)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3460231.3474255"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.crma.2012.03.014"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462978"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657908"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557624"},{"key":"e_1_3_2_1_10_1","first-page":"161","volume-title":"Machine Learning and Knowledge Discovery in Databases: European Conference, ECML PKDD 2013, Prague, Czech Republic, September 23-27, 2013, Proceedings, Part II 13","author":"Gao Sheng","year":"2013","unstructured":"Sheng Gao, Hao Luo, Da Chen, Shantao Li, Patrick Gallinari, and Jun Guo. 2013. Cross-domain recommendation via cluster-level latent factor model. In Machine Learning and Knowledge Discovery in Databases: European Conference, ECML PKDD 2013, Prague, Czech Republic, September 23-27, 2013, Proceedings, Part II 13. Springer, 161-176."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3523227.3546767"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Carlos A Gomez-Uribe and Neil Hunt. 2015. The netflix recommender system: Algorithms business value and innovation. ACM Transactions on Management Information Systems (TMIS)(2015).","DOI":"10.1145\/2843948"},{"key":"e_1_3_2_1_13_1","unstructured":"B Hidasi. 2015. Session-based Recommendations with Recurrent Neural Networks. arXiv preprint arXiv:1511.06939(2015)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3661348"},{"key":"e_1_3_2_1_15_1","unstructured":"Yupeng Hou Jiacheng Li Zhankui He An Yan Xiusi Chen and Julian McAuley. 2024a. Bridging Language and Items for Retrieval and Recommendation. arXiv preprint arXiv:2403.03952(2024)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-56060-6_24"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657685"},{"key":"e_1_3_2_1_18_1","unstructured":"Martin Jaggi. 2013. Revisiting Frank-Wolfe: Projection-free sparse convex optimization. In Procs. of ICML."},{"key":"e_1_3_2_1_19_1","unstructured":"Clark Mingxuan Ju Leonardo Neves Bhuvesh Kumar Liam Collins Tong Zhao Yuwei Qiu Qing Dou Yang Zhou Sohail Nizam Rengim Ozturk et al. 2025. Learning Universal User Representations Leveraging Cross-domain User Intent at Snapchat. arXiv preprint arXiv:2504.21838(2025)."},{"key":"e_1_3_2_1_20_1","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems.","author":"Ju Mingxuan","unstructured":"Mingxuan Ju, William Shiao, Zhichun Guo, Yanfang Ye, Yozen Liu, Neil Shah, and Tong Zhao. [n.d.]. How Does Message Passing Improve Collaborative Filtering?. In The Thirty-eighth Annual Conference on Neural Information Processing Systems."},{"key":"e_1_3_2_1_21_1","unstructured":"Mingxuan Ju Tong Zhao Qianlong Wen Wenhao Yu Neil Shah Yanfang Ye and Chuxu Zhang. 2023. Multi-task Self-supervised Graph Neural Networks Enable Stronger Task Generalization. In Procs. of ICLR."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2018.00035"},{"key":"e_1_3_2_1_23_1","volume-title":"Robust Training Objectives Improve Embedding-based Retrieval in Industrial Recommendation Systems. RobustRecSys Workshop at RecSys(2024)","author":"Kolodner Matthew","year":"2024","unstructured":"Matthew Kolodner, Mingxuan Ju, Zihao Fan, Tong Zhao, Elham Ghazizadeh, Yan Wu, Neil Shah, and Yozen Liu. 2024. Robust Training Objectives Improve Embedding-based Retrieval in Industrial Recommendation Systems. RobustRecSys Workshop at RecSys(2024)."},{"key":"e_1_3_2_1_24_1","volume-title":"International conference on machine learning. PMLR, 230-238","author":"Lee Giwoong","year":"2016","unstructured":"Giwoong Lee, Eunho Yang, and Sung Hwang. 2016. Asymmetric multi-task learning based on task relatedness and loss. In International conference on machine learning. PMLR, 230-238."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539597.3570379"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3132847.3132926"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3616855.3635801"},{"key":"e_1_3_2_1_28_1","volume-title":"Pareto multi-task learning. Advances in neural information processing systems","author":"Lin Xi","year":"2019","unstructured":"Xi Lin, Hui-Ling Zhen, Zhenhua Li, Qing-Fu Zhang, and Sam Kwong. 2019. Pareto multi-task learning. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591717"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412012"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219950"},{"key":"e_1_3_2_1_32_1","volume-title":"Mixed information flow for cross-domain sequential recommendations. ACM Transactions on Knowledge Discovery from Data (TKDD)","author":"Ma Muyang","year":"2022","unstructured":"Muyang Ma, Pengjie Ren, Zhumin Chen, Zhaochun Ren, Lifan Zhao, Peiyu Liu, Jun Ma, and Maarten de Rijke. 2022. Mixed information flow for cross-domain sequential recommendations. ACM Transactions on Knowledge Discovery from Data (TKDD), Vol. 16, 4 (2022), 1-32."},{"key":"e_1_3_2_1_33_1","volume-title":"Proceedings of the 42nd international ACM SIGIR conference on research and development in information retrieval. 685-694","author":"Ma Muyang","year":"2019","unstructured":"Muyang Ma, Pengjie Ren, Yujie Lin, Zhumin Chen, Jun Ma, and Maarten de Rijke. 2019.: A parallel information-sharing network for shared-account cross-domain sequential recommendations. In Proceedings of the 42nd international ACM SIGIR conference on research and development in information retrieval. 685-694."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766462.2767755"},{"key":"e_1_3_2_1_35_1","volume-title":"Attention bottlenecks for multimodal fusion. Advances in neural information processing systems","author":"Nagrani Arsha","year":"2021","unstructured":"Arsha Nagrani, Shan Yang, Anurag Arnab, Aren Jansen, Cordelia Schmid, and Chen Sun. 2021. Attention bottlenecks for multimodal fusion. Advances in neural information processing systems, Vol. 34 (2021), 14200-14213."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539156"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3614828"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657710"},{"key":"e_1_3_2_1_39_1","volume-title":"BPR: Bayesian personalized ranking from implicit feedback. In UAI.","author":"Rendle Steffen","year":"2009","unstructured":"Steffen Rendle, Christoph Freudenthaler, Zeno Gantner, and Lars Schmidt-Thieme. 2009. BPR: Bayesian personalized ranking from implicit feedback. In UAI."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3450120"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/336992.337035"},{"key":"e_1_3_2_1_42_1","volume-title":"Multi-task learning as multi-objective optimization. Advances in neural information processing systems","author":"Sener Ozan","year":"2018","unstructured":"Ozan Sener and Vladlen Koltun. 2018. Multi-task learning as multi-objective optimization. Advances in neural information processing systems, Vol. 31 (2018)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/1401890.1401969"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357895"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3437963.3441811"},{"key":"e_1_3_2_1_46_1","volume-title":"Proceedings of the conference. Association for computational linguistics. Meeting","volume":"2019","author":"Hubert Tsai Yao-Hung","year":"2019","unstructured":"Yao-Hung Hubert Tsai, Shaojie Bai, Paul Pu Liang, J Zico Kolter, Louis-Philippe Morency, and Ruslan Salakhutdinov. 2019. Multimodal transformer for unaligned multimodal language sequences. In Proceedings of the conference. Association for computational linguistics. Meeting, Vol. 2019. NIH Public Access, 6558."},{"key":"e_1_3_2_1_47_1","unstructured":"Aaron Van den Oord Sander Dieleman and Benjamin Schrauwen. 2013. Deep content-based music recommendation. In Procs. of NeurIPS."},{"key":"e_1_3_2_1_48_1","unstructured":"A Vaswani. 2017. Attention is all you need. Advances in Neural Information Processing Systems(2017)."},{"key":"e_1_3_2_1_49_1","volume-title":"Chi","author":"Wang Ruoxi","year":"2021","unstructured":"Ruoxi Wang, Rakesh Shivanna, Derek Cheng, Sagar Jain, Dong Lin, Lichan Hong, and Ed Chi. 2021. Dcn v2: Improved deep & cross network and practical lessons for web-scale learning to rank systems. In Procs. of WWW."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3018661.3018689"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11280-024-01291-2"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.10.066"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3275156"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"crossref","unstructured":"Rex Ying Ruining He Kaifeng Chen Pong Eksombatchai William L Hamilton and Jure Leskovec. 2018. Graph convolutional neural networks for web-scale recommender systems. In Procs. of SIGKDD.","DOI":"10.1145\/3219819.3219890"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3548455"},{"key":"e_1_3_2_1_56_1","unstructured":"Junjie Zhang Ruobing Xie Yupeng Hou Xin Zhao Leyu Lin and Ji-Rong Wen. 2023. Recommendation as instruction following: A large language model empowered recommendation approach. ACM Transactions on Information Systems(2023)."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.dss.2017.10.002"},{"key":"e_1_3_2_1_58_1","unstructured":"Yuyu Zhang Liang Pang Lei Shi and Bin Wang. 2014. Large scale purchase prediction with historical user actions on B2C online retail platform. arXiv preprint arXiv:1408.6515(2014)."},{"key":"e_1_3_2_1_59_1","volume-title":"MDMTRec: An Adaptive Multi-Task Multi-Domain Recommendation Framework. In 47th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR","author":"Zhang Zijian","year":"2024","unstructured":"Zijian Zhang, Shuchang Liu, Jiaao Yu, Qingpeng Cai, Xiangyu Zhao, Chunxu Zhang, Ziru Liu, Qidong Liu, Hongwei Zhao, Lantao Hu, et al., 2024. MDMTRec: An Adaptive Multi-Task Multi-Domain Recommendation Framework. In 47th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2024)."},{"key":"e_1_3_2_1_60_1","unstructured":"Wayne Xin Zhao Kun Zhou Junyi Li Tianyi Tang Xiaolei Wang Yupeng Hou Yingqian Min Beichen Zhang Junjie Zhang Zican Dong et al. 2023. A survey of large language models. arXiv preprint arXiv:2303.18223(2023)."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3411954"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357992"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"crossref","unstructured":"Feng Zhu Yan Wang Chaochao Chen Jun Zhou Longfei Li and Guanfeng Liu. 2021. Cross-domain recommendation: challenges progress and prospects. arXiv preprint arXiv:2103.01696(2021).","DOI":"10.24963\/ijcai.2021\/639"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657930"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645347"}],"event":{"name":"KDD '25: The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Toronto ON Canada","acronym":"KDD '25","sponsor":["SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3711896.3737108","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T18:07:34Z","timestamp":1777572454000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3711896.3737108"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,3]]},"references-count":65,"alternative-id":["10.1145\/3711896.3737108","10.1145\/3711896"],"URL":"https:\/\/doi.org\/10.1145\/3711896.3737108","relation":{},"subject":[],"published":{"date-parts":[[2025,8,3]]},"assertion":[{"value":"2025-08-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}