{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T05:46:15Z","timestamp":1777873575804,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100006374","name":"University Grants Committee","doi-asserted-by":"publisher","award":["17203320,17209822"],"award-info":[{"award-number":["17203320,17209822"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8,3]]},"DOI":"10.1145\/3711896.3737042","type":"proceedings-article","created":{"date-parts":[[2025,8,3]],"date-time":"2025-08-03T21:07:39Z","timestamp":1754255259000},"page":"3378-3389","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["MDVT: Enhancing Multimodal Recommendation with Model-Agnostic Multimodal-Driven Virtual Triplets"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-7876-3740","authenticated-orcid":false,"given":"Jinfeng","family":"Xu","sequence":"first","affiliation":[{"name":"Department of Electrical and Electronic Engineering, The University of Hong Kong, Hong Kong, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5779-3523","authenticated-orcid":false,"given":"Zheyu","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6749-5442","authenticated-orcid":false,"given":"Jinze","family":"Li","sequence":"additional","affiliation":[{"name":"The Department of Electrical and Electronic Engineering, The University of Hong Kong, Hong Kong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1638-9623","authenticated-orcid":false,"given":"Shuo","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, The University of Hong Kong, Hong Kong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6952-0886","authenticated-orcid":false,"given":"Hewei","family":"Wang","sequence":"additional","affiliation":[{"name":"Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2118-2280","authenticated-orcid":false,"given":"Yijie","family":"Li","sequence":"additional","affiliation":[{"name":"Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7540-530X","authenticated-orcid":false,"given":"Mengran","family":"Li","sequence":"additional","affiliation":[{"name":"School of Intelligent Systems Engineering, Sun Yat-sen University, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1510-215X","authenticated-orcid":false,"given":"Puzhen","family":"Wu","sequence":"additional","affiliation":[{"name":"Population Health Sciences, Weill Cornell Medicine, Cornell University, New York, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3454-8731","authenticated-orcid":false,"given":"Edith C. H.","family":"Ngai","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, University of Hong Kong, Hong Kong, China"}]}],"member":"320","published-online":{"date-parts":[[2025,8,3]]},"reference":[{"key":"e_1_3_2_2_1_1","series-title":"SIAM review","volume-title":"Optimization methods for large-scale machine learning","author":"Bottou L\u00e9on","year":"2018","unstructured":"L\u00e9on Bottou, Frank E Curtis, and Jorge Nocedal. 2018. Optimization methods for large-scale machine learning. SIAM review, Vol. 60, 2 (2018), 223-311."},{"key":"e_1_3_2_2_2_1","volume-title":"RapVerse: Coherent Vocals and Whole-Body Motions Generations from Text. arXiv preprint arXiv:2405.20336","author":"Chen Jiaben","year":"2024","unstructured":"Jiaben Chen, Xin Yan, Yihang Chen, Siyuan Cen, Qinwei Ma, Haoyu Zhen, Kaizhi Qian, Lie Lu, and Chuang Gan. 2024. RapVerse: Coherent Vocals and Whole-Body Motions Generations from Text. arXiv preprint arXiv:2405.20336 (2024)."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080797"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331254"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10887910"},{"key":"e_1_3_2_2_6_1","volume-title":"2025 b. Squeeze and Excitation: A Weighted Graph Contrastive Learning for Collaborative Filtering. arXiv preprint arXiv:2504.04443","author":"Chen Zheyu","year":"2025","unstructured":"Zheyu Chen, Jinfeng Xu, Yutong Wei, and Ziyue Peng. 2025 b. Squeeze and Excitation: A Weighted Graph Contrastive Learning for Collaborative Filtering. arXiv preprint arXiv:2504.04443 (2025)."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i8.28688"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.9973"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401063"},{"key":"e_1_3_2_2_10_1","volume-title":"Large Language Model Interaction Simulator for Cold-Start Item Recommendation. arXiv preprint arXiv:2402.09176","author":"Huang Feiran","year":"2024","unstructured":"Feiran Huang, Zhenghang Yang, Junyi Jiang, Yuanchen Bei, Yijie Zhang, and Hao Chen. 2024. Large Language Model Interaction Simulator for Cold-Start Item Recommendation. arXiv preprint arXiv:2402.09176 (2024)."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"crossref","unstructured":"Yangqin Jiang Lianghao Xia Wei Wei Da Luo Kangyi Lin and Chao Huang. 2024. DiffMM: Multi-Modal Diffusion Model for Recommendation. (2024).","DOI":"10.1145\/3664647.3681498"},{"key":"e_1_3_2_2_12_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_2_13_1","volume-title":"Visualizing the loss landscape of neural nets. Advances in neural information processing systems","author":"Li Hao","year":"2018","unstructured":"Hao Li, Zheng Xu, Gavin Taylor, Christoph Studer, and Tom Goldstein. 2018. Visualizing the loss landscape of neural nets. Advances in neural information processing systems, Vol. 31 (2018)."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371841"},{"key":"e_1_3_2_2_15_1","unstructured":"Zhiqiu Lin Siyuan Cen Daniel Jiang Jay Karhade Hewei Wang Chancharik Mitra Tiffany Ling Yuhan Huang Sifan Liu Mingyu Chen et al. 2025. Towards Understanding Camera Motions in Any Video. arXiv preprint arXiv:2504.15376 (2025)."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"crossref","unstructured":"Shang Liu Zhenzhong Chen Hongyi Liu and Xinghai Hu. 2019. User-video co-attention network for personalized micro-video recommendation. In The world wide web conference. 3020-3026.","DOI":"10.1145\/3308558.3313513"},{"key":"e_1_3_2_2_17_1","volume-title":"Integrating large language models into recommendation via mutual augmentation and adaptive aggregation. arXiv preprint arXiv:2401.13870","author":"Luo Sichun","year":"2024","unstructured":"Sichun Luo, Yuxuan Yao, Bowei He, Yinya Huang, Aojun Zhou, Xinyi Zhang, Yuanzhang Xiao, Mingjie Zhan, and Linqi Song. 2024. Integrating large language models into recommendation via mutual augmentation and adaptive aggregation. arXiv preprint arXiv:2401.13870 (2024)."},{"key":"e_1_3_2_2_18_1","volume-title":"XRec: Large Language Models for Explainable Recommendation. arXiv preprint arXiv:2406.02377","author":"Ma Qiyao","year":"2024","unstructured":"Qiyao Ma, Xubin Ren, and Chao Huang. 2024. XRec: Large Language Models for Explainable Recommendation. arXiv preprint arXiv:2406.02377 (2024)."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766462.2767755"},{"key":"e_1_3_2_2_20_1","volume-title":"Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence. 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 Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence. 452-461."},{"key":"e_1_3_2_2_21_1","volume-title":"International conference on machine learning. PMLR, 1139-1147","author":"Sutskever Ilya","year":"2013","unstructured":"Ilya Sutskever, James Martens, George Dahl, and Geoffrey Hinton. 2013. On the importance of initialization and momentum in deep learning. In International conference on machine learning. PMLR, 1139-1147."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2019.2893638"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3187556"},{"key":"e_1_3_2_2_24_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_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583206"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3616855.3635853"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413556"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351034"},{"key":"e_1_3_2_2_29_1","volume-title":"The marginal value of adaptive gradient methods in machine learning. Advances in neural information processing systems","author":"Wilson Ashia C","year":"2017","unstructured":"Ashia C Wilson, Rebecca Roelofs, Mitchell Stern, Nati Srebro, and Benjamin Recht. 2017. The marginal value of adaptive gradient methods in machine learning. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3679697"},{"key":"e_1_3_2_2_31_1","volume-title":"FourierKAN-GCF: Fourier Kolmogorov-Arnold Network-An Effective and Efficient Feature Transformation for Graph Collaborative Filtering. arXiv preprint arXiv:2406.01034","author":"Xu Jinfeng","year":"2024","unstructured":"Jinfeng Xu, Zheyu Chen, Jinze Li, Shuo Yang, Wei Wang, Xiping Hu, and Edith C-H Ngai. 2024b. FourierKAN-GCF: Fourier Kolmogorov-Arnold Network-An Effective and Efficient Feature Transformation for Graph Collaborative Filtering. arXiv preprint arXiv:2406.01034 (2024)."},{"key":"e_1_3_2_2_32_1","volume-title":"2025 a. COHESION: Composite Graph Convolutional Network with Dual-Stage Fusion for Multimodal Recommendation. arXiv preprint arXiv:2504.04452","author":"Xu Jinfeng","year":"2025","unstructured":"Jinfeng Xu, Zheyu Chen, Wei Wang, Xiping Hu, Sang-Wook Kim, and Edith CH Ngai. 2025 a. COHESION: Composite Graph Convolutional Network with Dual-Stage Fusion for Multimodal Recommendation. arXiv preprint arXiv:2504.04452 (2025)."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i12.33408"},{"key":"e_1_3_2_2_34_1","volume-title":"2025 c. A Survey on Multimodal Recommender Systems: Recent Advances and Future Directions. arXiv preprint arXiv:2502.15711","author":"Xu Jinfeng","year":"2025","unstructured":"Jinfeng Xu, Zheyu Chen, Shuo Yang, Jinze Li, Wei Wang, Xiping Hu, Steven Hoi, and Edith Ngai. 2025 c. A Survey on Multimodal Recommender Systems: Recent Advances and Future Directions. arXiv preprint arXiv:2502.15711 (2025)."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599320"},{"key":"e_1_3_2_2_36_1","volume-title":"The dawn of lmms: Preliminary explorations with gpt-4v (ision). arXiv preprint arXiv:2309.17421","author":"Yang Zhengyuan","year":"2023","unstructured":"Zhengyuan Yang, Linjie Li, Kevin Lin, Jianfeng Wang, Chung-Ching Lin, Zicheng Liu, and Lijuan Wang. 2023. The dawn of lmms: Preliminary explorations with gpt-4v (ision). arXiv preprint arXiv:2309.17421, Vol. 9, 1 (2023), 1."},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613915"},{"key":"e_1_3_2_2_38_1","first-page":"5824","article-title":"Gradient surgery for multi-task learning","volume":"33","author":"Yu Tianhe","year":"2020","unstructured":"Tianhe Yu, Saurabh Kumar, Abhishek Gupta, Sergey Levine, Karol Hausman, and Chelsea Finn. 2020. Gradient surgery for multi-task learning. Advances in Neural Information Processing Systems, Vol. 33 (2020), 5824-5836.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475259"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.3233\/FAIA230631"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3611380.3628561"},{"key":"e_1_3_2_2_42_1","volume-title":"MMRec: Simplifying Multimodal Recommendation. arXiv preprint arXiv:2302.03497","author":"Zhou Xin","year":"2023","unstructured":"Xin Zhou. 2023b. MMRec: Simplifying Multimodal Recommendation. arXiv preprint arXiv:2302.03497 (2023)."},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3369875"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611943"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583251"}],"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\/3711896.3737042","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T18:03:54Z","timestamp":1777572234000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3711896.3737042"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,3]]},"references-count":45,"alternative-id":["10.1145\/3711896.3737042","10.1145\/3711896"],"URL":"https:\/\/doi.org\/10.1145\/3711896.3737042","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"}}]}}