{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T13:10:21Z","timestamp":1775913021377,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":48,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,4,30]]},"DOI":"10.1145\/3543507.3583251","type":"proceedings-article","created":{"date-parts":[[2023,4,26]],"date-time":"2023-04-26T23:30:51Z","timestamp":1682551851000},"page":"845-854","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":208,"title":["Bootstrap Latent Representations for Multi-modal Recommendation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0948-8033","authenticated-orcid":false,"given":"Xin","family":"Zhou","sequence":"first","affiliation":[{"name":"Nanyang Technological University, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4056-4148","authenticated-orcid":false,"given":"Hongyu","family":"Zhou","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9031-9696","authenticated-orcid":false,"given":"Yong","family":"Liu","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7787-5644","authenticated-orcid":false,"given":"Zhiwei","family":"Zeng","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0300-3448","authenticated-orcid":false,"given":"Chunyan","family":"Miao","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6617-7034","authenticated-orcid":false,"given":"Pengwei","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7901-0222","authenticated-orcid":false,"given":"Yuan","family":"You","sequence":"additional","affiliation":[{"name":"Alibaba, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5579-5144","authenticated-orcid":false,"given":"Feijun","family":"Jiang","sequence":"additional","affiliation":[{"name":"Alibaba, China"}]}],"member":"320","published-online":{"date-parts":[[2023,4,30]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Signature verification using a\" siamese\" time delay neural network. Advances in neural information processing systems 6","author":"Bromley Jane","year":"1993","unstructured":"Jane Bromley, Isabelle Guyon, Yann LeCun, Eduard S\u00e4ckinger, and Roopak Shah. 1993. Signature verification using a\" siamese\" time delay neural network. Advances in neural information processing systems 6 (1993), 737\u2013744."},{"key":"e_1_3_2_1_2_1","volume-title":"International Conference on Machine Learning. PMLR, 1725\u20131735","author":"Chen Ming","year":"2020","unstructured":"Ming Chen, Zhewei Wei, Zengfeng Huang, Bolin Ding, and Yaliang Li. 2020. Simple and deep graph convolutional networks. In International Conference on Machine Learning. PMLR, 1725\u20131735."},{"key":"e_1_3_2_1_3_1","volume-title":"International Conference on Machine Learning. 1597\u20131607","author":"Chen Ting","year":"2020","unstructured":"Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. In International Conference on Machine Learning. 1597\u20131607."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331254"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of the thirteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings, 249\u2013256","author":"Glorot Xavier","year":"2010","unstructured":"Xavier Glorot and Yoshua Bengio. 2010. Understanding the difficulty of training deep feedforward neural networks. In Proceedings of the thirteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings, 249\u2013256."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2872427.2883037"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.9973"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401063"},{"key":"e_1_3_2_1_11_1","first-page":"9895","article-title":"Sparse is enough in scaling transformers","volume":"34","author":"Jaszczur Sebastian","year":"2021","unstructured":"Sebastian Jaszczur, Aakanksha Chowdhery, Afroz Mohiuddin, Lukasz Kaiser, Wojciech Gajewski, Henryk Michalewski, and Jonni Kanerva. 2021. Sparse is enough in scaling transformers. Advances in Neural Information Processing Systems 34 (2021), 9895\u20139907.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2992393"},{"key":"e_1_3_2_1_13_1","volume-title":"International Conference on Learning Representations.","author":"Kingma P","year":"2015","unstructured":"Diederik\u00a0P Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_14_1","volume-title":"International Conference on Learning Representations.","author":"Kipf N","year":"2017","unstructured":"Thomas\u00a0N Kipf and Max Welling. 2017. Semi-supervised classification with graph convolutional networks. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462935"},{"key":"e_1_3_2_1_16_1","volume-title":"International conference on machine learning. PMLR, 6437\u20136449","author":"Li Guohao","year":"2021","unstructured":"Guohao Li, Matthias M\u00fcller, Bernard Ghanem, and Vladlen Koltun. 2021. Training graph neural networks with 1000 layers. In International conference on machine learning. PMLR, 6437\u20136449."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350953"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403076"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080658"},{"key":"e_1_3_2_1_20_1","volume-title":"Self-supervised learning: Generative or contrastive","author":"Liu Xiao","year":"2021","unstructured":"Xiao Liu, Fanjin Zhang, Zhenyu Hou, Li Mian, Zhaoyu Wang, Jing Zhang, and Jie Tang. 2021. Self-supervised learning: Generative or contrastive. IEEE Transactions on Knowledge and Data Engineering (2021)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1018"},{"key":"e_1_3_2_1_22_1","volume-title":"Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems 32","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, 2019. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_2_1_23_1","volume-title":"Sentence-bert: Sentence embeddings using siamese bert-networks. In EMNLP. 3980\u20133990.","author":"Reimers Nils","year":"2019","unstructured":"Nils Reimers and Iryna Gurevych. 2019. Sentence-bert: Sentence embeddings using siamese bert-networks. In EMNLP. 3980\u20133990."},{"key":"e_1_3_2_1_24_1","volume-title":"Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence. 452\u2013461","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 Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence. 452\u2013461."},{"key":"e_1_3_2_1_25_1","volume-title":"Visual Attention Emerges from Recurrent Sparse Reconstruction. arXiv preprint arXiv:2204.10962","author":"Shi Baifeng","year":"2022","unstructured":"Baifeng Shi, Yale Song, Neel Joshi, Trevor Darrell, and Xin Wang. 2022. Visual Attention Emerges from Recurrent Sparse Reconstruction. arXiv preprint arXiv:2204.10962 (2022)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0197-0"},{"key":"e_1_3_2_1_27_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)."},{"key":"e_1_3_2_1_28_1","volume-title":"Dropout: a simple way to prevent neural networks from overfitting. The journal of machine learning research 15, 1","author":"Srivastava Nitish","year":"2014","unstructured":"Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever, and Ruslan Salakhutdinov. 2014. Dropout: a simple way to prevent neural networks from overfitting. The journal of machine learning research 15, 1 (2014), 1929\u20131958."},{"key":"e_1_3_2_1_29_1","unstructured":"Antti Tarvainen and Harri Valpola. 2017. Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. Advances in neural information processing systems 30."},{"key":"e_1_3_2_1_30_1","volume-title":"International Conference on Learning Representations.","author":"Thakoor Shantanu","year":"2021","unstructured":"Shantanu Thakoor, Corentin Tallec, Mohammad\u00a0Gheshlaghi Azar, Mehdi Azabou, Eva\u00a0L Dyer, Remi Munos, Petar Veli\u010dkovi\u0107, and Michal Valko. 2021. Large-Scale Representation Learning on Graphs via Bootstrapping. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_31_1","volume-title":"DualGNN: Dual Graph Neural Network for Multimedia Recommendation","author":"Wang Qifan","year":"2021","unstructured":"Qifan Wang, Yinwei Wei, Jianhua Yin, Jianlong Wu, Xuemeng Song, and Liqiang Nie. 2021. DualGNN: Dual Graph Neural Network for Multimedia Recommendation. IEEE Transactions on Multimedia (2021)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/630"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413556"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351034"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462862"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462862"},{"key":"e_1_3_2_1_37_1","volume-title":"Graph neural networks in recommender systems: a survey. ACM Computing Surveys (CSUR)","author":"Wu Shiwen","year":"2020","unstructured":"Shiwen Wu, Fei Sun, Wentao Zhang, Xu Xie, and Bin Cui. 2020. Graph neural networks in recommender systems: a survey. ACM Computing Surveys (CSUR) (2020)."},{"key":"e_1_3_2_1_38_1","volume-title":"Barlow twins: Self-supervised learning via redundancy reduction. arXiv preprint arXiv:2103.03230","author":"Zbontar Jure","year":"2021","unstructured":"Jure Zbontar, Li Jing, Ishan Misra, Yann LeCun, and St\u00e9phane Deny. 2021. Barlow twins: Self-supervised learning via redundancy reduction. arXiv preprint arXiv:2103.03230 (2021)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475259"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-00126-0_15"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3158369"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/2484028.2484126"},{"key":"e_1_3_2_1_43_1","volume-title":"A Comprehensive Survey on Multimodal Recommender Systems: Taxonomy, Evaluation, and Future Directions. arXiv preprint arXiv:2302.04473","author":"Zhou Hongyu","year":"2023","unstructured":"Hongyu Zhou, Xin Zhou, Zhiwei Zeng, Lingzi Zhang, and Zhiqi Shen. 2023. A Comprehensive Survey on Multimodal Recommender Systems: Taxonomy, Evaluation, and Future Directions. arXiv preprint arXiv:2302.04473 (2023)."},{"key":"e_1_3_2_1_44_1","volume-title":"Enhancing Dyadic Relations with Homogeneous Graphs for Multimodal Recommendation. arXiv preprint arXiv:2301.12097","author":"Zhou Hongyu","year":"2023","unstructured":"Hongyu Zhou, Xin Zhou, Lingzi Zhang, and Zhiqi Shen. 2023. Enhancing Dyadic Relations with Homogeneous Graphs for Multimodal Recommendation. arXiv preprint arXiv:2301.12097 (2023)."},{"key":"e_1_3_2_1_45_1","volume-title":"A Tale of Two Graphs: Freezing and Denoising Graph Structures for Multimodal Recommendation. arXiv preprint arXiv:2211.06924","author":"Zhou Xin","year":"2022","unstructured":"Xin Zhou. 2022. A Tale of Two Graphs: Freezing and Denoising Graph Structures for Multimodal Recommendation. arXiv preprint arXiv:2211.06924 (2022)."},{"key":"e_1_3_2_1_46_1","volume-title":"MMRec: Simplifying Multimodal Recommendation. arXiv preprint arXiv:2302.03497","author":"Zhou Xin","year":"2023","unstructured":"Xin Zhou. 2023. MMRec: Simplifying Multimodal Recommendation. arXiv preprint arXiv:2302.03497 (2023)."},{"key":"e_1_3_2_1_47_1","volume-title":"Layer-refined Graph Convolutional Networks for Recommendation. arXiv preprint arXiv:2207.11088","author":"Zhou Xin","year":"2022","unstructured":"Xin Zhou, Donghui Lin, Yong Liu, and Chunyan Miao. 2022. Layer-refined Graph Convolutional Networks for Recommendation. arXiv preprint arXiv:2207.11088 (2022)."},{"key":"e_1_3_2_1_48_1","volume-title":"SelfCF: A Simple Framework for Self-supervised Collaborative Filtering. arXiv preprint arXiv:2107.03019","author":"Zhou Xin","year":"2021","unstructured":"Xin Zhou, Aixin Sun, Yong Liu, Jie Zhang, and Chunyan Miao. 2021. SelfCF: A Simple Framework for Self-supervised Collaborative Filtering. arXiv preprint arXiv:2107.03019 (2021)."}],"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\/3543507.3583251","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3543507.3583251","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:37:22Z","timestamp":1750178242000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3543507.3583251"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,30]]},"references-count":48,"alternative-id":["10.1145\/3543507.3583251","10.1145\/3543507"],"URL":"https:\/\/doi.org\/10.1145\/3543507.3583251","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"}}]}}