{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T20:13:51Z","timestamp":1783541631856,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"the Oversea In- novation Team Project of the 20 Regulations for New Universities funding program of Jinan","award":["2021GXRC073"],"award-info":[{"award-number":["2021GXRC073"]}]},{"name":"the TaiShan Scholars Program","award":["tsqn202211289"],"award-info":[{"award-number":["tsqn202211289"]}]},{"name":"the Excellent Youth Scholars Program of Shandong Province","award":["2022HWYQ-048"],"award-info":[{"award-number":["2022HWYQ-048"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,13]]},"DOI":"10.1145\/3589335.3651956","type":"proceedings-article","created":{"date-parts":[[2024,5,12]],"date-time":"2024-05-12T18:41:21Z","timestamp":1715539281000},"page":"1733-1740","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":25,"title":["Multimodal Conditioned Diffusion Model for Recommendation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4621-5213","authenticated-orcid":false,"given":"Haokai","family":"Ma","sequence":"first","affiliation":[{"name":"School of Software, Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5375-8397","authenticated-orcid":false,"given":"Yimeng","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Software, Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0273-5946","authenticated-orcid":false,"given":"Lei","family":"Meng","sequence":"additional","affiliation":[{"name":"Shandong Research Institute of Industrial Technology & School of Software, Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3170-5647","authenticated-orcid":false,"given":"Ruobing","family":"Xie","sequence":"additional","affiliation":[{"name":"WeChat, Tencent, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7290-5659","authenticated-orcid":false,"given":"Xiangxu","family":"Meng","sequence":"additional","affiliation":[{"name":"School of Software, Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,5,13]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"One transformer fits all distributions in multi-modal diffusion at scale. arXiv preprint arXiv:2303.06555","author":"Bao Fan","year":"2023","unstructured":"Fan Bao, Shen Nie, Kaiwen Xue, Chongxuan Li, Shi Pu, Yaole Wang, Gang Yue, Yue Cao, Hang Su, and Jun Zhu. 2023. One transformer fits all distributions in multi-modal diffusion at scale. arXiv preprint arXiv:2303.06555 (2023)."},{"key":"e_1_3_2_2_2_1","volume-title":"Label-efficient semantic segmentation with diffusion models. arXiv preprint arXiv:2112.03126","author":"Baranchuk Dmitry","year":"2021","unstructured":"Dmitry Baranchuk, Ivan Rubachev, Andrey Voynov, Valentin Khrulkov, and Artem Babenko. 2021. Label-efficient semantic segmentation with diffusion models. arXiv preprint arXiv:2112.03126 (2021)."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591994"},{"key":"e_1_3_2_2_4_1","volume-title":"Understanding the difficulty of training deep feedforward neural networks. Journal of Machine Learning Research (JMLR)","author":"Glorot Xavier","year":"2010","unstructured":"Xavier Glorot and Yoshua Bengio. 2010. Understanding the difficulty of training deep feedforward neural networks. Journal of Machine Learning Research (JMLR) (2010)."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.9973"},{"key":"e_1_3_2_2_6_1","unstructured":"Xiangnan He Kuan Deng Xiang Wang Yan Li Yongdong Zhang and Meng Wang. 2020. LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation. (2020)."},{"key":"e_1_3_2_2_7_1","volume-title":"Denoising Diffusion Probabilistic Models. Neural Information Processing Systems,Neural Information Processing Systems","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, AjayN. Jain, and Pieter Abbeel. 2020. Denoising Diffusion Probabilistic Models. Neural Information Processing Systems,Neural Information Processing Systems (2020)."},{"key":"e_1_3_2_2_8_1","volume-title":"Kingma and Jimmy Ba","author":"Diederik","year":"2014","unstructured":"Diederik P. Kingma and Jimmy Ba. 2014. Adam: A Method for Stochastic Optimization. CoRR , Vol. abs\/1412.6980 (2014)."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.01.029"},{"key":"e_1_3_2_2_10_1","unstructured":"XiangLisa Li John Thickstun Ishaan Gulrajani Percy Liang and TatsunoriB. Hashimoto. 2022a. Diffusion-LM Improves Controllable Text Generation. (2022)."},{"key":"e_1_3_2_2_11_1","unstructured":"Zihao Li Aixin Sun and Chenliang Li. 2023. DiffuRec: A Diffusion Model for Sequential Recommendation. (2023)."},{"key":"e_1_3_2_2_12_1","volume-title":"Diffusion Augmentation for Sequential Recommendation. In In Proceedings of the 32nd ACM International Conference on Information and Knowledge Management (CIKM).","author":"Liu Qidong","year":"2023","unstructured":"Qidong Liu, Fan Yan, Xiangyu Zhao, Zhaocheng Du, Huifeng Guo, Ruiming Tang, and Feng Tian. 2023. Diffusion Augmentation for Sequential Recommendation. In In Proceedings of the 32nd ACM International Conference on Information and Knowledge Management (CIKM)."},{"key":"e_1_3_2_2_13_1","unstructured":"Romain Lopez Pierre Boyeau Nir Yosef Michael I. Jordan and Jeffrey Regier. 2020. AUTO-ENCODING VARIATIONAL BAYES."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3475724.3483600"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN54540.2023.10191979"},{"key":"e_1_3_2_2_16_1","volume-title":"Plug-in Diffusion Model for Sequential Recommendation. arXiv preprint arXiv:2401.02913","author":"Ma Haokai","year":"2024","unstructured":"Haokai Ma, Ruobing Xie, Lei Meng, Xin Chen, Xu Zhang, Leyu Lin, and Zhanhui Kang. 2024. Plug-in Diffusion Model for Sequential Recommendation. arXiv preprint arXiv:2401.02913 (2024)."},{"key":"e_1_3_2_2_17_1","volume-title":"Exploring False Hard Negative Sample in Cross-Domain Recommendation. In In Proceedings of the ACM Conference on Recommender Systems (Recsys).","author":"Ma Haokai","year":"2023","unstructured":"Haokai Ma, Ruobing Xie, Lei Meng, Xin Chen, Xu Zhang, Leyu Lin, and Jie Zhou. 2023 b. Exploring False Hard Negative Sample in Cross-Domain Recommendation. In In Proceedings of the ACM Conference on Recommender Systems (Recsys)."},{"key":"e_1_3_2_2_18_1","volume-title":"2023 c. Triple Sequence Learning for Cross-domain Recommendation. ACM Transactions on Information Systems (TOIS)","author":"Ma Haokai","year":"2023","unstructured":"Haokai Ma, Ruobing Xie, Lei Meng, Xin Chen, Xu Zhang, Leyu Lin, and Jie Zhou. 2023 c. Triple Sequence Learning for Cross-domain Recommendation. ACM Transactions on Information Systems (TOIS) (2023)."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413598"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"e_1_3_2_2_21_1","volume-title":"BPR: Bayesian personalized ranking from implicit feedback. Uncertainty in Artificial Intelligence,Uncertainty in Artificial Intelligence","author":"Rendle Steffen","year":"2009","unstructured":"Steffen Rendle, Christoph Freudenthaler, Zeno Gantner, and Lars Schmidt-Thieme. 2009. BPR: Bayesian personalized ranking from implicit feedback. Uncertainty in Artificial Intelligence,Uncertainty in Artificial Intelligence (2009)."},{"key":"e_1_3_2_2_22_1","volume-title":"High-Resolution Image Synthesis with Latent Diffusion Models. In 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Rombach Robin","year":"2022","unstructured":"Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, and Bjorn Ommer. 2022. High-Resolution Image Synthesis with Latent Diffusion Models. In 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_2_23_1","volume-title":"DropEdge: Towards Deep Graph Convolutional Networks on Node Classification. Learning,Learning","author":"Rong Yu","year":"2019","unstructured":"Yu Rong, Wenbing Huang, Tingyang Xu, and Junzhou Huang. 2019. DropEdge: Towards Deep Graph Convolutional Networks on Node Classification. Learning,Learning (2019)."},{"key":"e_1_3_2_2_24_1","series-title":"Lecture Notes in Computer Science,Lecture Notes in Computer Science","volume-title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","author":"Ronneberger Olaf","year":"2015","unstructured":"Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-Net: Convolutional Networks for Biomedical Image Segmentation. Lecture Notes in Computer Science,Lecture Notes in Computer Science (2015)."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3187556"},{"key":"e_1_3_2_2_26_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 (JMLR), Vol. 9, 11 (2008).","journal-title":"Journal of Machine Learning Research (JMLR)"},{"key":"e_1_3_2_2_27_1","volume-title":"2023 a. DualGNN: Dual Graph Neural Network for Multimedia Recommendation","author":"Wang Qifan","year":"2023","unstructured":"Qifan Wang, Yinwei Wei, Jianhua Yin, Jianlong Wu, Xuemeng Song, and Liqiang Nie. 2023 a. DualGNN: Dual Graph Neural Network for Multimedia Recommendation. IEEE Transactions on Multimedia (2023)."},{"key":"e_1_3_2_2_28_1","volume-title":"Diffusion Recommender Model. In In Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR).","author":"Wang Wenjie","year":"2023","unstructured":"Wenjie Wang, Yiyan Xu, Fuli Feng, Xinyu Lin, Xiangnan He, and Tat-Seng Chua. 2023 b. Diffusion Recommender Model. In In Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351034"},{"key":"e_1_3_2_2_30_1","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems.","author":"Yang Zhengyi","year":"2023","unstructured":"Zhengyi Yang, Jiancan Wu, Zhicai Wang, Xiang Wang, Yancheng Yuan, and Xiangnan He. 2023. Generate What You Prefer: Reshaping Sequential Recommendation via Guided Diffusion. In Thirty-seventh Conference on Neural Information Processing Systems."},{"key":"e_1_3_2_2_31_1","volume-title":"LD4MRec: Simplifying and Powering Diffusion Model for Multimedia Recommendation. arXiv preprint arXiv:2309.15363","author":"Yu Penghang","year":"2023","unstructured":"Penghang Yu, Zhiyi Tan, Guanming Lu, and Bing-Kun Bao. 2023. LD4MRec: Simplifying and Powering Diffusion Model for Multimedia Recommendation. arXiv preprint arXiv:2309.15363 (2023)."},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-srw.12"},{"key":"e_1_3_2_2_33_1","volume-title":"Mining Latent Structures for Multimedia Recommendation. In In Proceedings of the 29th ACM International Conference on Multimedia (MM).","author":"Zhang Jinghao","year":"2021","unstructured":"Jinghao Zhang, Yanqiao Zhu, Qiang Liu, Shu Wu, Shuhui Wang, and Liang Wang. 2021. Mining Latent Structures for Multimedia Recommendation. In In Proceedings of the 29th ACM International Conference on Multimedia (MM)."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611943"},{"key":"e_1_3_2_2_35_1","volume-title":"Bootstrap Latent Representations for Multi-modal Recommendation. In In Proceedings of the ACM Web Conference 2023 (WWW). iogr","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 In Proceedings of the ACM Web Conference 2023 (WWW). iogr"}],"event":{"name":"WWW '24: The ACM Web Conference 2024","location":"Singapore Singapore","acronym":"WWW '24","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Companion Proceedings of the ACM Web Conference 2024"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3589335.3651956","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3589335.3651956","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:35:59Z","timestamp":1755822959000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3589335.3651956"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":35,"alternative-id":["10.1145\/3589335.3651956","10.1145\/3589335"],"URL":"https:\/\/doi.org\/10.1145\/3589335.3651956","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]},"assertion":[{"value":"2024-05-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}