{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T10:20:36Z","timestamp":1784370036914,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":49,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,4,30]],"date-time":"2023-04-30T00:00:00Z","timestamp":1682812800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"APRC - CityU New Research Initiatives","award":["No.9610565"],"award-info":[{"award-number":["No.9610565"]}]},{"name":"Huawei Innovation Research Program"},{"name":"HKIDS Early Career Research Grant","award":["No.9360163"],"award-info":[{"award-number":["No.9360163"]}]},{"name":"Ant Group (CCF-Ant Research Fund)"},{"name":"SIRG - CityU Strategic Interdisciplinary Research Grant","award":["No.7020046, No.7020074"],"award-info":[{"award-number":["No.7020046, No.7020074"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,4,30]]},"DOI":"10.1145\/3543507.3583378","type":"proceedings-article","created":{"date-parts":[[2023,4,26]],"date-time":"2023-04-26T23:30:51Z","timestamp":1682551851000},"page":"1109-1117","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":53,"title":["MMMLP: Multi-modal Multilayer Perceptron for\u00a0Sequential\u00a0Recommendations"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5187-4718","authenticated-orcid":false,"given":"Jiahao","family":"Liang","sequence":"first","affiliation":[{"name":"City University of Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2926-4416","authenticated-orcid":false,"given":"Xiangyu","family":"Zhao","sequence":"additional","affiliation":[{"name":"City University of Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1009-2343","authenticated-orcid":false,"given":"Muyang","family":"Li","sequence":"additional","affiliation":[{"name":"University of Sydney, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1194-8334","authenticated-orcid":false,"given":"Zijian","family":"Zhang","sequence":"additional","affiliation":[{"name":"Jilin University, China and City University of Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"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"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5290-7163","authenticated-orcid":false,"given":"Haochen","family":"Liu","sequence":"additional","affiliation":[{"name":"Michigan State University, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0491-307X","authenticated-orcid":false,"given":"Zitao","family":"Liu","sequence":"additional","affiliation":[{"name":"Guangdong Institute of Smart Education, Jinan University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,4,30]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"E. Bugliarello R. Cotterell N. Okazaki and D. Elliott. 2020. Multimodal Pretraining Unmasked: Unifying the Vision and Language BERTs. (2020)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080797"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"K. Cho B\u00a0Van Merrienboer C. Gulcehre D. Bahdanau F. Bougares H. Schwenk and Y. Bengio. 2014. Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation. Computer Science (2014).","DOI":"10.3115\/v1\/D14-1179"},{"key":"e_1_3_2_1_4_1","volume-title":"A hybrid online-product recommendation system: Combining implicit rating-based collaborative filtering and sequential pattern analysis. electronic commerce research and applications 11, 4","author":"Choi Keunho","year":"2012","unstructured":"Keunho Choi, Donghee Yoo, Gunwoo Kim, and Yongmoo Suh. 2012. A hybrid online-product recommendation system: Combining implicit rating-based collaborative filtering and sequential pattern analysis. electronic commerce research and applications 11, 4 (2012), 309\u2013317."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-00126-0_2"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"F. Fusco D. Pascual and P. Staar. 2022. pNLP-Mixer: an Efficient all-MLP Architecture for Language. (2022).","DOI":"10.18653\/v1\/2023.acl-industry.6"},{"key":"e_1_3_2_1_7_1","volume-title":"Sequential recommendation with a pre-trained module learning multi-modal information. In 2020 International Conferences on Internet of Things (iThings) and IEEE Green Computing and Communications","author":"Han Tengyue","unstructured":"Tengyue Han, Yu Tian, Jiwei Zhang, and Shaozhang Niu. 2020. Sequential recommendation with a pre-trained module learning multi-modal information. In 2020 International Conferences on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData) and IEEE Congress on Cybermatics (Cybermatics). IEEE, 611\u2013616."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2016.0030"},{"key":"e_1_3_2_1_9_1","volume-title":"Gaussian error linear units (gelus). arXiv preprint arXiv:1606.08415","author":"Hendrycks Dan","year":"2016","unstructured":"Dan Hendrycks and Kevin Gimpel. 2016. Gaussian error linear units (gelus). arXiv preprint arXiv:1606.08415 (2016)."},{"key":"e_1_3_2_1_10_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_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959167"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_1_13_1","volume-title":"CSAN: Contextual Self-Attention Network for User Sequential Recommendation. In 2018 ACM Multimedia Conference.","author":"Huang X.","unstructured":"X. Huang, S. Qian, F. Quan, J. Sang, and C. Xu. 2018. CSAN: Contextual Self-Attention Network for User Sequential Recommendation. In 2018 ACM Multimedia Conference."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2487575.2487589"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2018.00035"},{"key":"e_1_3_2_1_16_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_17_1","volume-title":"MLP4Rec: A Pure MLP Architecture for Sequential Recommendations. arXiv preprint arXiv:2204.11510","author":"Li Muyang","year":"2022","unstructured":"Muyang Li, Xiangyu Zhao, Chuan Lyu, Minghao Zhao, Runze Wu, and Ruocheng Guo. 2022. MLP4Rec: A Pure MLP Architecture for Sequential Recommendations. arXiv preprint arXiv:2204.11510 (2022)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"X. Li C. Wang J. Tan X. Zeng D. Ou and B. Zheng. 2020. Adversarial Multimodal Representation Learning for Click-Through Rate Prediction.","DOI":"10.1145\/3366423.3380163"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2009.06.004"},{"key":"e_1_3_2_1_20_1","unstructured":"H. Liu Z. Dai D.\u00a0R. So and Q.\u00a0V. Le. 2021. Pay Attention to MLPs."},{"key":"e_1_3_2_1_21_1","volume-title":"Sequential Heterogeneous Attribute Embedding for Item Recommendation. In 2017 IEEE International Conference on Data Mining Workshops (ICDMW).","author":"Liu K.","unstructured":"K. Liu, S. Xing, and P. Natarajan. 2017. Sequential Heterogeneous Attribute Embedding for Item Recommendation. In 2017 IEEE International Conference on Data Mining Workshops (ICDMW)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2016.0135"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","unstructured":"F. Mai A. Pannatier F. Fehr H. Chen F. Marelli F. Fleuret and J. Henderson. 2022. HyperMixer: An MLP-based Green AI Alternative to Transformers. (2022).","DOI":"10.18653\/v1\/2023.acl-long.871"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330666"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2010.127"},{"key":"e_1_3_2_1_26_1","volume-title":"Proc. of Uncertainty in Artificial Intelligence. 452\u2013461","author":"Rendle Steffen","year":"2014","unstructured":"Steffen Rendle, Christoph Freudenthaler, Zeno Gantner, and Lars\u00a0BPR Schmidt-Thieme. 2014. Bayesian personalized ranking from implicit feedback. In Proc. of Uncertainty in Artificial Intelligence. 452\u2013461."},{"key":"e_1_3_2_1_27_1","volume-title":"AutoAssign: Automatic Shared Embedding Assignment in Streaming Recommendation. In 2022 IEEE International Conference on Data Mining (ICDM). IEEE, 458\u2013467","author":"Song Fengyi","year":"2022","unstructured":"Fengyi Song, Bo Chen, Xiangyu Zhao, Huifeng Guo, and Ruiming Tang. 2022. AutoAssign: Automatic Shared Embedding Assignment in Streaming Recommendation. In 2022 IEEE International Conference on Data Mining (ICDM). IEEE, 458\u2013467."},{"key":"e_1_3_2_1_28_1","volume-title":"Web page recommendation approach using weighted sequential patterns and Markov model. Global Journal of Computer Science and Technology","author":"Suneetha K","year":"2012","unstructured":"K Suneetha and M\u00a0Usha Rani. 2012. Web page recommendation approach using weighted sequential patterns and Markov model. Global Journal of Computer Science and Technology (2012)."},{"key":"e_1_3_2_1_29_1","unstructured":"C. Tang Y. Zhao G. Wang C. Luo W. Xie and W. Zeng. 2021. Sparse MLP for Image Recognition: Is Self-Attention Really Necessary?arXiv e-prints (2021)."},{"key":"e_1_3_2_1_30_1","first-page":"24261","article-title":"Mlp-mixer: An all-mlp architecture for vision","volume":"34","author":"Tolstikhin O","year":"2021","unstructured":"Ilya\u00a0O Tolstikhin, Neil Houlsby, Alexander Kolesnikov, Lucas Beyer, Xiaohua Zhai, Thomas Unterthiner, Jessica Yung, Andreas Steiner, Daniel Keysers, Jakob Uszkoreit, 2021. Mlp-mixer: An all-mlp architecture for vision. Advances in Neural Information Processing Systems 34 (2021), 24261\u201324272.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_31_1","unstructured":"H. Touvron P. Bojanowski M. Caron M. Cord A. El-Nouby E. Grave G. Izacard A. Joulin G. Synnaeve and J. Verbeek. 2021. ResMLP: Feedforward networks for image classification with data-efficient training. (2021)."},{"key":"e_1_3_2_1_32_1","unstructured":"A. Vaswani N. Shazeer N. Parmar J. Uszkoreit L. Jones A.\u00a0N. Gomez L. Kaiser and I. Polosukhin. 2017. Attention Is All You Need. In arXiv."},{"key":"e_1_3_2_1_33_1","volume-title":"Decoupled Side Information Fusion for Sequential Recommendation. arXiv preprint arXiv:2204.11046","author":"Xie Yueqi","year":"2022","unstructured":"Yueqi Xie, Peilin Zhou, and Sunghun Kim. 2022. Decoupled Side Information Fusion for Sequential Recommendation. arXiv preprint arXiv:2204.11046 (2022)."},{"key":"e_1_3_2_1_34_1","unstructured":"P. Yu M. Artetxe M. Ott S. Shleifer H. Gong V. Stoyanov and X. Li. 2022. Efficient Language Modeling with Sparse all-MLP. (2022)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557348"},{"key":"e_1_3_2_1_36_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_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557461"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482016"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i1.16156"},{"key":"e_1_3_2_1_40_1","volume-title":"Deep reinforcement learning for search, recommendation, and online advertising: a survey. ACM SIGWEB NewsletterSpring","author":"Zhao Xiangyu","year":"2019","unstructured":"Xiangyu Zhao, Long Xia, Jiliang Tang, and Dawei Yin. 2019. Deep reinforcement learning for search, recommendation, and online advertising: a survey. ACM SIGWEB NewsletterSpring (2019), 1\u201315."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240323.3240374"},{"key":"e_1_3_2_1_42_1","volume-title":"Whole-Chain Recommendations. In Proceedings of the 29th ACM International Conference on Information & Knowledge Management. 1883\u20131891","author":"Zhao Xiangyu","year":"2020","unstructured":"Xiangyu Zhao, Long Xia, Lixin Zou, Hui Liu, Dawei Yin, and Jiliang Tang. 2020. Whole-Chain Recommendations. In Proceedings of the 29th ACM International Conference on Information & Knowledge Management. 1883\u20131891."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3450125"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219886"},{"key":"e_1_3_2_1_45_1","volume-title":"Deep Reinforcement Learning for List-wise Recommendations. arXiv preprint arXiv:1801.00209","author":"Zhao Xiangyu","year":"2017","unstructured":"Xiangyu Zhao, Liang Zhang, Zhuoye Ding, Dawei Yin, Yihong Zhao, and Jiliang Tang. 2017. Deep Reinforcement Learning for List-wise Recommendations. arXiv preprint arXiv:1801.00209 (2017)."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403384"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512111"},{"key":"e_1_3_2_1_48_1","volume-title":"Using temporal data for making recommendations. arXiv preprint arXiv:1301.2320","author":"Zimdars Andrew","year":"2013","unstructured":"Andrew Zimdars, David\u00a0Maxwell Chickering, and Christopher Meek. 2013. Using temporal data for making recommendations. arXiv preprint arXiv:1301.2320 (2013)."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401181"}],"event":{"name":"WWW '23: The ACM Web Conference 2023","location":"Austin TX USA","acronym":"WWW '23","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM Web Conference 2023"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3543507.3583378","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3543507.3583378","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:37:23Z","timestamp":1750178243000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3543507.3583378"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,30]]},"references-count":49,"alternative-id":["10.1145\/3543507.3583378","10.1145\/3543507"],"URL":"https:\/\/doi.org\/10.1145\/3543507.3583378","relation":{},"subject":[],"published":{"date-parts":[[2023,4,30]]},"assertion":[{"value":"2023-04-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}