{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:38:42Z","timestamp":1778081922404,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":47,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Research Foundation, Singapore"},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272254 & 62236003"],"award-info":[{"award-number":["62272254 & 62236003"]}],"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":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681148","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:49Z","timestamp":1729925989000},"page":"9660-9669","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":13,"title":["Attribute-driven Disentangled Representation Learning for Multimodal Recommendation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4694-1231","authenticated-orcid":false,"given":"Zhenyang","family":"Li","sequence":"first","affiliation":[{"name":"Shandong University, Qingdao, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4547-3982","authenticated-orcid":false,"given":"Fan","family":"Liu","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1791-3159","authenticated-orcid":false,"given":"Yinwei","family":"Wei","sequence":"additional","affiliation":[{"name":"Monash University, Melbourne, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1109-5028","authenticated-orcid":false,"given":"Zhiyong","family":"Cheng","sequence":"additional","affiliation":[{"name":"Hefei University of Technology, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1476-0273","authenticated-orcid":false,"given":"Liqiang","family":"Nie","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4846-2015","authenticated-orcid":false,"given":"Mohan","family":"Kankanhalli","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331254"},{"key":"e_1_3_2_1_2_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In North American","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In North American Chapter of the Association for Computational Linguistics. ACL, 4171--4186."},{"key":"e_1_3_2_1_3_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly Jakob Uszkoreit and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In ICLR. OpenReview.net."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539597.3570405"},{"key":"e_1_3_2_1_5_1","volume-title":"Collaborative Memory Network for Recommendation Systems. In International Conference on Research and Development in Information Retrieval. ACM, 515--524","author":"Ebesu Travis","year":"2018","unstructured":"Travis Ebesu, Bin Shen, and Yi Fang. 2018. Collaborative Memory Network for Recommendation Systems. In International Conference on Research and Development in Information Retrieval. ACM, 515--524."},{"key":"e_1_3_2_1_6_1","volume-title":"Zero-shot Synthesis with Group-Supervised Learning. In International Conference on Learning Representations.","author":"Ge Yunhao","year":"2021","unstructured":"Yunhao Ge, Sami Abu-El-Haija, Gan Xin, and Laurent Itti. 2021. Zero-shot Synthesis with Group-Supervised Learning. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_7_1","volume-title":"International Conference on Artificial Intelligence and Statistics","volume":"9","author":"Glorot Xavier","year":"2010","unstructured":"Xavier Glorot and Yoshua Bengio. 2010. Understanding the difficulty of training deep feedforward neural networks. In International Conference on Artificial Intelligence and Statistics, Vol. 9. JMLR, 249--256."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3358415"},{"key":"e_1_3_2_1_9_1","unstructured":"William L. Hamilton Zhitao Ying and Jure Leskovec. 2017. Inductive Representation Learning on Large Graphs. In Advances in Neural Information Processing Systems. 1024--1034."},{"key":"e_1_3_2_1_10_1","volume-title":"AAAI Conference on Artificial Intelligence, Dale Schuurmans and Michael P. Wellman (Eds.). AAAI, 144--150","author":"He Ruining","unstructured":"Ruining He and Julian J. McAuley. 2016. VBPR: Visual Bayesian Personalized Ranking from Implicit Feedback. In AAAI Conference on Artificial Intelligence, Dale Schuurmans and Michael P. Wellman (Eds.). AAAI, 144--150."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401063"},{"key":"e_1_3_2_1_12_1","volume-title":"Neural Collaborative Filtering. In International Conference on World Wide Web. ACM, 173--182","author":"He Xiangnan","year":"2017","unstructured":"Xiangnan He, Lizi Liao, Hanwang Zhang, Liqiang Nie, Xia Hu, and Tat-Seng Chua. 2017. Neural Collaborative Filtering. In International Conference on World Wide Web. ACM, 173--182."},{"key":"e_1_3_2_1_13_1","volume-title":"International Conference on Learning Representations.","author":"Higgins Irina","year":"2017","unstructured":"Irina Higgins, Lo\"ic Matthey, Arka Pal, Christopher P. Burgess, Xavier Glorot, Matthew M. Botvinick, Shakir Mohamed, and Alexander Lerchner. 2017. beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_14_1","volume-title":"Collaborative Metric Learning. In International Conference on World Wide Web. ACM, 193--201","author":"Hsieh Cheng-Kang","year":"2017","unstructured":"Cheng-Kang Hsieh, Longqi Yang, Yin Cui, Tsung-Yi Lin, Serge J. Belongie, and Deborah Estrin. 2017. Collaborative Metric Learning. In International Conference on World Wide Web. ACM, 193--201."},{"key":"e_1_3_2_1_15_1","unstructured":"Jun-Ting Hsieh Bingbin Liu De-An Huang Li Fei-Fei and Juan Carlos Niebles. 2018. Learning to Decompose and Disentangle Representations for Video Prediction. In Advances in Neural Information Processing Systems. 515--524."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","unstructured":"Yannis Kalantidis Lyndon Kennedy and Li-Jia Li. 2013. Getting the look: clothing recognition and segmentation for automatic product suggestions in everyday photos. In ICMR. ACM 105--112.","DOI":"10.1145\/2461466.2461485"},{"key":"e_1_3_2_1_17_1","volume-title":"Adam: A Method for Stochastic Optimization. In International Conference on Learning Representations.","author":"Diederik","unstructured":"Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_18_1","volume-title":"Auto-Encoding Variational Bayes. In International Conference on Learning Representations.","author":"Diederik","unstructured":"Diederik P. Kingma and Max Welling. 2014. Auto-Encoding Variational Bayes. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3217449"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611886"},{"key":"e_1_3_2_1_21_1","volume-title":"International Conference on Multimedia. ACM, 1526--1534","author":"Liu Fan","unstructured":"Fan Liu, Zhiyong Cheng, Changchang Sun, Yinglong Wang, Liqiang Nie, and Mohan S. Kankanhalli. 2019. User Diverse Preference Modeling by Multimodal Attentive Metric Learning. In International Conference on Multimedia. ACM, 1526--1534."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449986"},{"key":"e_1_3_2_1_23_1","article-title":"Dynamic Multimodal Fusion via Meta-Learning Towards Micro-Video Recommendation","volume":"42","author":"Liu Han","year":"2023","unstructured":"Han Liu, Yinwei Wei, Fan Liu, Wenjie Wang, Liqiang Nie, and Tat-Seng Chua. 2023. Dynamic Multimodal Fusion via Meta-Learning Towards Micro-Video Recommendation. ACM Transactions on Information Systems, Vol. 42, 2, Article 47 (2023), 26 pages.","journal-title":"ACM Transactions on Information Systems"},{"key":"e_1_3_2_1_24_1","volume-title":"Independence Promoted Graph Disentangled Networks. In AAAI Conference on Artificial Intelligence. AAAI, 4916--4923","author":"Liu Yanbei","year":"2020","unstructured":"Yanbei Liu, Xiao Wang, Shu Wu, and Zhitao Xiao. 2020. Independence Promoted Graph Disentangled Networks. In AAAI Conference on Artificial Intelligence. AAAI, 4916--4923."},{"key":"e_1_3_2_1_25_1","unstructured":"Jianxin Ma Chang Zhou Peng Cui Hongxia Yang and Wenwu Zhu. 2019. Learning Disentangled Representations for Recommendation. In Advances in Neural Information Processing Systems. 5712--5723."},{"key":"e_1_3_2_1_26_1","volume-title":"ACM Conference on Recommender Systems. ACM, 165--172","author":"Julian","unstructured":"Julian J. McAuley and Jure Leskovec. 2013. Hidden factors and hidden topics: understanding rating dimensions with review text. In ACM Conference on Recommender Systems. ACM, 165--172."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3464304"},{"key":"e_1_3_2_1_28_1","volume-title":"Learning from Multiple Social Networks. Synthesis Lectures on Information Concepts Retrieval & Services","author":"Nie Liqiang","year":"2016","unstructured":"Liqiang Nie, Xuemeng Song, and Tat Seng Chua. 2016. Learning from Multiple Social Networks. Synthesis Lectures on Information Concepts Retrieval & Services (2016), 1--118."},{"key":"e_1_3_2_1_29_1","volume-title":"PyTorch: An Imperative Style","author":"Paszke Adam","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas K\u00f6pf, Edward Yang, Zachary DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala. 2019. PyTorch: An Imperative Style, High-Performance Deep Learning Library. In Advances in Neural Information Processing Systems. 8024--8035."},{"key":"e_1_3_2_1_30_1","volume-title":"Factorization Machines. In International Conference on Data Mining. IEEE, 995--1000","author":"Rendle Steffen","year":"2010","unstructured":"Steffen Rendle. 2010. Factorization Machines. In International Conference on Data Mining. IEEE, 995--1000."},{"key":"e_1_3_2_1_31_1","volume-title":"Conference on Uncertainty in Artificial Intelligence. ACM, 452--461","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 Conference on Uncertainty in Artificial Intelligence. ACM, 452--461."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/371920.372071"},{"key":"e_1_3_2_1_33_1","volume-title":"Rating-boosted latent topics: Understanding users and items with ratings and reviews","author":"Tan Yunzhi","unstructured":"Yunzhi Tan, Min Zhang, Yiqun Liu, and Shaoping Ma. 2016. Rating-boosted latent topics: Understanding users and items with ratings and reviews. In IJCAI. AAAI Press."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3186154"},{"key":"e_1_3_2_1_35_1","volume-title":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (Washington DC, USA) (KDD '22)","author":"Tran Nhu-Thuat","year":"1806","unstructured":"Nhu-Thuat Tran and Hady W. Lauw. 2022. Aligning Dual Disentangled User Representations from Ratings and Textual Content. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (Washington DC, USA) (KDD '22). ACM, 1798--1806."},{"key":"e_1_3_2_1_36_1","first-page":"2579","article-title":"Visualizing Data using t-SNE","volume":"9","author":"van der Maaten Laurens","year":"2008","unstructured":"Laurens van der Maaten and Geoffrey E. Hinton. 2008. Visualizing Data using t-SNE. Journal of Machine Learning Research, Vol. 9 (2008), 2579--2605.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3153112"},{"key":"e_1_3_2_1_38_1","volume-title":"Neural Graph Collaborative Filtering. In International Conference on Research and Development in Information Retrieval. ACM, 165--174","author":"Wang Xiang","year":"2019","unstructured":"Xiang Wang, Xiangnan He, Meng Wang, Fuli Feng, and Tat-Seng Chua. 2019. Neural Graph Collaborative Filtering. In International Conference on Research and Development in Information Retrieval. ACM, 165--174."},{"key":"e_1_3_2_1_39_1","volume-title":"Disentangled Graph Collaborative Filtering. In International Conference on Research and Development in Information Retrieval. ACM, 1001--1010","author":"Wang Xiang","year":"2020","unstructured":"Xiang Wang, Hongye Jin, An Zhang, Xiangnan He, Tong Xu, and Tat-Seng Chua. 2020. Disentangled Graph Collaborative Filtering. In International Conference on Research and Development in Information Retrieval. ACM, 1001--1010."},{"key":"e_1_3_2_1_40_1","volume-title":"LightGT: A Light Graph Transformer for Multimedia Recommendation. In International Conference on Research and Development in Information Retrieval. ACM, 1508--1517","author":"Wei Yinwei","year":"2023","unstructured":"Yinwei Wei, Wenqi Liu, Fan Liu, Xiang Wang, Liqiang Nie, and Tat-Seng Chua. 2023. LightGT: A Light Graph Transformer for Multimedia Recommendation. In International Conference on Research and Development in Information Retrieval. ACM, 1508--1517."},{"key":"e_1_3_2_1_41_1","volume-title":"Graph-Refined Convolutional Network for Multimedia Recommendation with Implicit Feedback. In International Conference on Multimedia. ACM, 3541--3549","author":"Wei Yinwei","year":"2020","unstructured":"Yinwei Wei, Xiang Wang, Liqiang Nie, Xiangnan He, and Tat-Seng Chua. 2020. Graph-Refined Convolutional Network for Multimedia Recommendation with Implicit Feedback. In International Conference on Multimedia. ACM, 3541--3549."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351034"},{"key":"e_1_3_2_1_43_1","volume-title":"Collaborative Knowledge Base Embedding for Recommender Systems. In International Conference on Knowledge Discovery and Data Mining. ACM, 353--362","author":"Zhang Fuzheng","year":"2016","unstructured":"Fuzheng Zhang, Nicholas Jing Yuan, Defu Lian, Xing Xie, and Wei-Ying Ma. 2016. Collaborative Knowledge Base Embedding for Recommender Systems. In International Conference on Knowledge Discovery and Data Mining. ACM, 353--362."},{"key":"e_1_3_2_1_44_1","volume-title":"International Conference on Research and Development in Information Retrieval. ACM, 1684--1693","author":"Zhang Xiaokun","year":"2022","unstructured":"Xiaokun Zhang, Bo Xu, Liang Yang, Chenliang Li, Fenglong Ma, Haifeng Liu, and Hongfei Lin. 2022. Price DOES Matter! Modeling Price and Interest Preferences in Session-Based Recommendation. In International Conference on Research and Development in Information Retrieval. ACM, 1684--1693."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"crossref","unstructured":"Yongfeng Zhang Qingyao Ai Xu Chen and W Bruce Croft. 2017. Joint representation learning for top-n recommendation with heterogeneous information sources. In CIKM. ACM 1449--1458.","DOI":"10.1145\/3132847.3132892"},{"key":"e_1_3_2_1_46_1","volume-title":"Joint Representation Learning for Top-N Recommendation with Heterogeneous Information Sources. In International Conference on Information and Knowledge Management. ACM, 1449--1458","author":"Zhang Yongfeng","unstructured":"Yongfeng Zhang, Qingyao Ai, Xu Chen, and W. Bruce Croft. 2017. Joint Representation Learning for Top-N Recommendation with Heterogeneous Information Sources. In International Conference on Information and Knowledge Management. ACM, 1449--1458."},{"key":"e_1_3_2_1_47_1","volume-title":"Bootstrap Latent Representations for Multi-modal Recommendation. In International World Wide Web Conference. ACM, 845--854","author":"Zhou Xin","year":"2023","unstructured":"Xin Zhou, Hongyu Zhou, Yong Liu, Zhiwei Zeng, Chunyan Miao, Pengwei Wang, Yuan You, and Feijun Jiang. 2023. Bootstrap Latent Representations for Multi-modal Recommendation. In International World Wide Web Conference. ACM, 845--854."}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681148","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681148","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:57:53Z","timestamp":1750294673000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681148"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":47,"alternative-id":["10.1145\/3664647.3681148","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681148","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}