{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T21:28:37Z","timestamp":1783114117081,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":50,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T00:00:00Z","timestamp":1729468800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Young Top-notch Talent Cultivation Program of Hubei Province"},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272349"],"award-info":[{"award-number":["62272349"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,21]]},"DOI":"10.1145\/3627673.3679647","type":"proceedings-article","created":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T19:34:21Z","timestamp":1729452861000},"page":"1336-1345","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Spectral and Geometric Spaces Representation Regularization for Multi-Modal Sequential Recommendation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-7840-3364","authenticated-orcid":false,"given":"Zihao","family":"Li","sequence":"first","affiliation":[{"name":"Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1407-749X","authenticated-orcid":false,"given":"Xuekong","family":"Xu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8335-1157","authenticated-orcid":false,"given":"Zuoli","family":"Tang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6755-871X","authenticated-orcid":false,"given":"Lixin","family":"Zou","sequence":"additional","affiliation":[{"name":"Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8967-8525","authenticated-orcid":false,"given":"Qian","family":"Wang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3144-6374","authenticated-orcid":false,"given":"Chenliang","family":"Li","sequence":"additional","affiliation":[{"name":"Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,21]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Armen Aghajanyan Akshat Shrivastava Anchit Gupta Naman Goyal Luke Zettlemoyer and Sonal Gupta. 2020. Better Fine-Tuning by Reducing Representational Collapse. In ICLR."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Amir Beck. 2017. First-order methods in optimization. SIAM.","DOI":"10.1137\/1.9781611974997"},{"key":"e_1_3_2_1_3_1","volume-title":"Jinpeng Wang, Chuyuan Wang, and Ji-Rong Wen.","author":"Bian Shuqing","year":"2023","unstructured":"Shuqing Bian, Xingyu Pan, Wayne Xin Zhao, Jinpeng Wang, Chuyuan Wang, and Ji-Rong Wen. 2023. Multi-modal Mixture of Experts Represetation Learning for Sequential Recommendation. In CIKM. 110--119."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1137\/1104012"},{"key":"e_1_3_2_1_5_1","volume-title":"Rethinking Attention: Exploring Shallow Feed-Forward Neural Networks as an Alternative to Attention Layers in Transformers. arXiv preprint arXiv:2311.10642","author":"Bozic Vukasin","year":"2023","unstructured":"Vukasin Bozic, Danilo Dordevic, Daniele Coppola, Joseph Thommes, and Sidak Pal Singh. 2023. Rethinking Attention: Exploring Shallow Feed-Forward Neural Networks as an Alternative to Attention Layers in Transformers. arXiv preprint arXiv:2311.10642 (2023)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Huiyuan Chen Vivian Lai Hongye Jin Zhimeng Jiang Mahashweta Das and Xia Hu. 2024. Towards mitigating dimensional collapse of representations in collaborative filtering. In WSDM. 106--115.","DOI":"10.1145\/3616855.3635832"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"Xu Chen Hongteng Xu Yongfeng Zhang Jiaxi Tang Yixin Cao Zheng Qin and Hongyuan Zha. 2018. Sequential recommendation with user memory networks. In WSDM. 108--116.","DOI":"10.1145\/3159652.3159668"},{"key":"e_1_3_2_1_8_1","volume-title":"Fine-tuning pretrained language models: Weight initializations, data orders, and early stopping. arXiv preprint arXiv:2002.06305","author":"Dodge Jesse","year":"2020","unstructured":"Jesse Dodge, Gabriel Ilharco, Roy Schwartz, Ali Farhadi, Hannaneh Hajishirzi, and Noah Smith. 2020. Fine-tuning pretrained language models: Weight initializations, data orders, and early stopping. arXiv preprint arXiv:2002.06305 (2020)."},{"key":"e_1_3_2_1_9_1","volume-title":"Words: Transformers for Image Recognition at Scale. In ICLR.","author":"Dosovitskiy Alexey","year":"2020","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, et al. 2020. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In ICLR."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Shijie Geng Shuchang Liu Zuohui Fu Yingqiang Ge and Yongfeng Zhang. 2022. Recommendation as language processing (rlp): A unified pretrain personalized prompt & predict paradigm (p5). In RecSys. 299--315.","DOI":"10.1145\/3523227.3546767"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.644"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/342"},{"key":"e_1_3_2_1_13_1","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep residual learning for image recognition. In CVPR. 770--778."},{"key":"e_1_3_2_1_14_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_15_1","volume-title":"Yaliang Li, Bolin Ding, and Ji-Rong Wen.","author":"Hou Yupeng","year":"2022","unstructured":"Yupeng Hou, Shanlei Mu, Wayne Xin Zhao, Yaliang Li, Bolin Ding, and Ji-Rong Wen. 2022. Towards universal sequence representation learning for recommender systems. In KDD. 585--593."},{"key":"e_1_3_2_1_16_1","volume-title":"SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization. In ACL. 2177--2190.","author":"Jiang Haoming","year":"2020","unstructured":"Haoming Jiang, Pengcheng He, Weizhu Chen, Xiaodong Liu, Jianfeng Gao, and Tuo Zhao. 2020. SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization. In ACL. 2177--2190."},{"key":"e_1_3_2_1_17_1","volume-title":"Fundamentals of the theory of operator algebras. Volume II: Advanced theory","author":"Kadison Richard V","unstructured":"Richard V Kadison and John R Ringrose. 1986. Fundamentals of the theory of operator algebras. Volume II: Advanced theory. Academic press New York."},{"key":"e_1_3_2_1_18_1","volume-title":"Self-attentive sequential recommendation","author":"Kang Wang-Cheng","unstructured":"Wang-Cheng Kang and Julian McAuley. 2018. Self-attentive sequential recommendation. In ICDM. IEEE, 197--206."},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings of NAACL-HLT. 4171--4186","author":"Ming-Wei Chang Jacob Devlin","year":"2019","unstructured":"Jacob Devlin Ming-Wei Chang Kenton and Lee Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of NAACL-HLT. 4171--4186."},{"key":"e_1_3_2_1_20_1","volume-title":"Reformer: The Efficient Transformer. In ICLR.","author":"Kitaev Nikita","year":"2019","unstructured":"Nikita Kitaev, Lukasz Kaiser, and Anselm Levskaya. 2019. Reformer: The Efficient Transformer. In ICLR."},{"key":"e_1_3_2_1_21_1","volume-title":"En-compactness: Self-distillation embedding & contrastive generation for generalized zero-shot learning. In CVPR. 9306--9315.","author":"Kong Xia","year":"2022","unstructured":"Xia Kong, Zuodong Gao, Xiaofan Li, Ming Hong, Jun Liu, Chengjie Wang, Yuan Xie, and Yanyun Qu. 2022. En-compactness: Self-distillation embedding & contrastive generation for generalized zero-shot learning. In CVPR. 9306--9315."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3535335"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","unstructured":"Jiacheng Li Ming Wang Jin Li Jinmiao Fu Xin Shen Jingbo Shang and Julian McAuley. 2023. Text is all you need: Learning language representations for sequential recommendation. In KDD. 1258--1267.","DOI":"10.1145\/3580305.3599519"},{"key":"e_1_3_2_1_24_1","first-page":"1","article-title":"Diffurec: A diffusion model for sequential recommendation","volume":"42","author":"Li Zihao","year":"2023","unstructured":"Zihao Li, Aixin Sun, and Chenliang Li. 2023. Diffurec: A diffusion model for sequential recommendation. ACM Transactions on Information Systems, Vol. 42, 3 (2023), 1--28.","journal-title":"ACM Transactions on Information Systems"},{"key":"e_1_3_2_1_25_1","volume-title":"MMMLP: Multi-modal Multilayer Perceptron for Sequential Recommendations. In WWW. 1109--1117.","author":"Liang Jiahao","year":"2023","unstructured":"Jiahao Liang, Xiangyu Zhao, Muyang Li, Zijian Zhang, Wanyu Wang, Haochen Liu, and Zitao Liu. 2023. MMMLP: Multi-modal Multilayer Perceptron for Sequential Recommendations. In WWW. 1109--1117."},{"key":"e_1_3_2_1_26_1","volume-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. Advances in neural information processing systems","author":"Lu Jiasen","year":"2019","unstructured":"Jiasen Lu, Dhruv Batra, Devi Parikh, and Stefan Lee. 2019. Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.936"},{"key":"e_1_3_2_1_28_1","unstructured":"Ruihong Qiu Zi Huang Hongzhi Yin and Zijian Wang. 2022. Contrastive learning for representation degeneration problem in sequential recommendation. In WSDM. 813--823."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.5555\/3455716.3455856"},{"key":"e_1_3_2_1_30_1","unstructured":"Aditya Ramesh Mikhail Pavlov Gabriel Goh Scott Gray Chelsea Voss Alec Radford Mark Chen and Ilya Sutskever. 2021. Zero-shot text-to-image generation. In ICML. PMLR 8821--8831."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.975"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"crossref","unstructured":"Steffen Rendle Christoph Freudenthaler and Lars Schmidt-Thieme. 2010. Factorizing personalized markov chains for next-basket recommendation. In WWW. 811--820.","DOI":"10.1145\/1772690.1772773"},{"key":"e_1_3_2_1_33_1","article-title":"An MDP-based recommender system","volume":"6","author":"Shani Guy","year":"2005","unstructured":"Guy Shani, David Heckerman, Ronen I Brafman, and Craig Boutilier. 2005. An MDP-based recommender system. Journal of Machine Learning Research, Vol. 6, 9 (2005).","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"crossref","unstructured":"Fei Sun Jun Liu Jian Wu Changhua Pei Xiao Lin Wenwu Ou and Peng Jiang. 2019. BERT4Rec: Sequential recommendation with bidirectional encoder representations from transformer. In CIKM. 1441--1450.","DOI":"10.1145\/3357384.3357895"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","unstructured":"Christian Szegedy Wei Liu Yangqing Jia Pierre Sermanet Scott Reed Dragomir Anguelov Dumitru Erhan Vincent Vanhoucke and Andrew Rabinovich. 2015. Going deeper with convolutions. In CVPR. 1--9.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16564"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"crossref","unstructured":"Jiaxi Tang and Ke Wang. 2018. Personalized top-n sequential recommendation via convolutional sequence embedding. In WSDM. 565--573.","DOI":"10.1145\/3159652.3159656"},{"key":"e_1_3_2_1_38_1","volume-title":"One model for all: Large language models are domain-agnostic recommendation systems. arXiv preprint arXiv:2310.14304","author":"Tang Zuoli","year":"2023","unstructured":"Zuoli Tang, Zhaoxin Huan, Zihao Li, Xiaolu Zhang, Jun Hu, Chilin Fu, Jun Zhou, and Chenliang Li. 2023. One model for all: Large language models are domain-agnostic recommendation systems. arXiv preprint arXiv:2310.14304 (2023)."},{"key":"e_1_3_2_1_39_1","article-title":"Visualizing data using t-SNE","volume":"9","author":"der Maaten Laurens Van","year":"2008","unstructured":"Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of machine learning research, Vol. 9, 11 (2008).","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_1_40_1","volume-title":"NeurIPS","volume":"30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. NeurIPS, Vol. 30 (2017)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"crossref","unstructured":"Jianling Wang Kaize Ding Liangjie Hong Huan Liu and James Caverlee. 2020. Next-item recommendation with sequential hypergraphs. In SIGIR. 1101--1110.","DOI":"10.1145\/3397271.3401133"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"crossref","unstructured":"Jinpeng Wang Ziyun Zeng Yunxiao Wang Yuting Wang Xingyu Lu Tianxiang Li Jun Yuan Rui Zhang Hai-Tao Zheng and Shu-Tao Xia. 2023. MISSRec: Pre-training and Transferring Multi-modal Interest-aware Sequence Representation for Recommendation. In MM. 6548--6557.","DOI":"10.1145\/3581783.3611967"},{"key":"e_1_3_2_1_43_1","unstructured":"Tongzhou Wang and Phillip Isola. 2020. Understanding contrastive representation learning through alignment and uniformity on the hypersphere. In ICML. PMLR 9929--9939."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"crossref","unstructured":"Yihua Wen Si Chen Yu Tian Wanxian Guan Pengjie Wang Hongbo Deng Jian Xu Bo Zheng Zihao Li Lixin Zou et al. 2024. Unified Visual Preference Learning for User Intent Understanding. In WSDM. 816--825.","DOI":"10.1145\/3616855.3635858"},{"key":"e_1_3_2_1_45_1","volume-title":"Mm-rec: multimodal news recommendation. arXiv preprint arXiv:2104.07407","author":"Wu Chuhan","year":"2021","unstructured":"Chuhan Wu, Fangzhao Wu, Tao Qi, and Yongfeng Huang. 2021. Mm-rec: multimodal news recommendation. arXiv preprint arXiv:2104.07407 (2021)."},{"key":"e_1_3_2_1_46_1","volume-title":"Workshop on Advancing Neural Network Training: Computational Efficiency, Scalability, and Resource Optimization (WANT@ NeurIPS","author":"Xia Mengzhou","year":"2023","unstructured":"Mengzhou Xia, Tianyu Gao, Zhiyuan Zeng, and Danqi Chen. 2023. Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning. In Workshop on Advancing Neural Network Training: Computational Efficiency, Scalability, and Resource Optimization (WANT@ NeurIPS 2023)."},{"key":"e_1_3_2_1_47_1","volume-title":"Contrastive learning for sequential recommendation","author":"Xie Xu","unstructured":"Xu Xie, Fei Sun, Zhaoyang Liu, Shiwen Wu, Jinyang Gao, Jiandong Zhang, Bolin Ding, and Bin Cui. 2022. Contrastive learning for sequential recommendation. In ICDE. IEEE, 1259--1273."},{"key":"e_1_3_2_1_48_1","volume-title":"TruthSR: Trustworthy Sequential Recommender Systems via User-generated Multimodal Content. arXiv preprint arXiv:2404.17238","author":"Yan Meng","year":"2024","unstructured":"Meng Yan, Haibin Huang, Ying Liu, Juan Zhao, Xiyue Gao, Cai Xu, Ziyu Guan, and Wei Zhao. 2024. TruthSR: Trustworthy Sequential Recommender Systems via User-generated Multimodal Content. arXiv preprint arXiv:2404.17238 (2024)."},{"key":"e_1_3_2_1_49_1","volume-title":"Beyond Co-occurrence: Multi-modal Session-based Recommendation","author":"Zhang Xiaokun","year":"2023","unstructured":"Xiaokun Zhang, Bo Xu, Fenglong Ma, Chenliang Li, Liang Yang, and Hongfei Lin. 2023. Beyond Co-occurrence: Multi-modal Session-based Recommendation. IEEE Transactions on Knowledge and Data Engineering (2023)."},{"key":"e_1_3_2_1_50_1","volume-title":"Yutao Zhu, Sirui Wang, Fuzheng Zhang, Zhongyuan Wang, and Ji-Rong Wen.","author":"Zhou Kun","year":"2020","unstructured":"Kun Zhou, Hui Wang, Wayne Xin Zhao, Yutao Zhu, Sirui Wang, Fuzheng Zhang, Zhongyuan Wang, and Ji-Rong Wen. 2020. S3-rec: Self-supervised learning for sequential recommendation with mutual information maximization. In CIKM. 1893--1902."}],"event":{"name":"CIKM '24: The 33rd ACM International Conference on Information and Knowledge Management","location":"Boise ID USA","acronym":"CIKM '24","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 33rd ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627673.3679647","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3627673.3679647","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:58:12Z","timestamp":1750294692000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627673.3679647"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,21]]},"references-count":50,"alternative-id":["10.1145\/3627673.3679647","10.1145\/3627673"],"URL":"https:\/\/doi.org\/10.1145\/3627673.3679647","relation":{},"subject":[],"published":{"date-parts":[[2024,10,21]]},"assertion":[{"value":"2024-10-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}