{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T15:31:06Z","timestamp":1784388666848,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":53,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,13]]},"DOI":"10.1145\/3726302.3729949","type":"proceedings-article","created":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T01:18:36Z","timestamp":1752455916000},"page":"581-591","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["Diffusion-based Multi-modal Synergy Interest Network for Click-through Rate Prediction"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-4639-1278","authenticated-orcid":false,"given":"Xiaoxi","family":"Cui","sequence":"first","affiliation":[{"name":"Takway.AI, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1783-5518","authenticated-orcid":false,"given":"Weihai","family":"Lu","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5487-9671","authenticated-orcid":false,"given":"Yu","family":"Tong","sequence":"additional","affiliation":[{"name":"Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0622-0196","authenticated-orcid":false,"given":"Yiheng","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai University of International Business, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9498-3839","authenticated-orcid":false,"given":"Zhejun","family":"Zhao","sequence":"additional","affiliation":[{"name":"Microsoft, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,7,13]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539170"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599922"},{"key":"e_1_3_2_1_3_1","volume-title":"End-to-end user behavior retrieval in click-through rateprediction model. arXiv preprint arXiv:2108.04468","author":"Chen Qiwei","year":"2021","unstructured":"Qiwei Chen, Changhua Pei, Shanshan Lv, Chao Li, Junfeng Ge, and Wenwu Ou. 2021. End-to-end user behavior retrieval in click-through rateprediction model. arXiv preprint arXiv:2108.04468 (2021)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3326937.3341261"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2988450.2988454"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959190"},{"key":"e_1_3_2_1_7_1","unstructured":"Xiuqi Deng Lu Xu Xiyao Li Jinkai Yu Erpeng Xue Zhongyuan Wang Di Zhang Zhaojie Liu Guorui Zhou Yang Song et al. 2024. End-to-end training of Multimodal Model and ranking Model. arXiv preprint arXiv:2404.06078 (2024)."},{"key":"e_1_3_2_1_8_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_9_1","volume-title":"An introduction to ROC analysis. Pattern recognition letters","author":"Fawcett Tom","year":"2006","unstructured":"Tom Fawcett. 2006. An introduction to ROC analysis. Pattern recognition letters, Vol. 27, 8 (2006), 861--874."},{"key":"e_1_3_2_1_10_1","volume-title":"Deep session interest network for click-through rate prediction. arXiv preprint arXiv:1905.06482","author":"Feng Yufei","year":"2019","unstructured":"Yufei Feng, Fuyu Lv, Weichen Shen, Menghan Wang, Fei Sun, Yu Zhu, and Keping Yang. 2019. Deep session interest network for click-through rate prediction. arXiv preprint arXiv:1905.06482 (2019)."},{"key":"e_1_3_2_1_11_1","unstructured":"Huifeng Guo Ruiming Tang Yunming Ye Zhenguo Li and Xiuqiang He. 2017. DeepFM: a factorization-machine based neural network for CTR prediction. arXiv preprint arXiv:1703.04247 (2017)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICTAI56018.2022.00025"},{"key":"e_1_3_2_1_13_1","volume-title":"Denoising diffusion probabilistic models. Advances in neural information processing systems","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems, Vol. 33 (2020), 6840--6851."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583434"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539381"},{"key":"e_1_3_2_1_16_1","volume-title":"Adaptive Multi-Modalities Fusion in Sequential Recommendation Systems. arXiv preprint arXiv:2308.15980","author":"Hu Hengchang","year":"2023","unstructured":"Hengchang Hu, Wei Guo, Yong Liu, and Min-Yen Kan. 2023. Adaptive Multi-Modalities Fusion in Sequential Recommendation Systems. arXiv preprint arXiv:2308.15980 (2023)."},{"key":"e_1_3_2_1_17_1","volume-title":"Online Distillation-enhanced Multi-modal Transformer for Sequential Recommendation. arXiv preprint arXiv:2308.04067","author":"Ji Wei","year":"2023","unstructured":"Wei Ji, Xiangyan Liu, An Zhang, Yinwei Wei, Yongxin Ni, and Xiang Wang. 2023. Online Distillation-enhanced Multi-modal Transformer for Sequential Recommendation. arXiv preprint arXiv:2308.04067 (2023)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3616855.3635850"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462878"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681203"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380163"},{"key":"e_1_3_2_1_22_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_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220023"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16549"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3615134"},{"key":"e_1_3_2_1_26_1","volume-title":"Paul Pu Liang, Amir Zadeh, and Louis-Philippe Morency.","author":"Liu Zhun","year":"2018","unstructured":"Zhun Liu, Ying Shen, Varun Bharadhwaj Lakshminarasimhan, Paul Pu Liang, Amir Zadeh, and Louis-Philippe Morency. 2018. Efficient low-rank multimodal fusion with modality-specific factors. arXiv preprint arXiv:1806.00064 (2018)."},{"key":"e_1_3_2_1_27_1","volume-title":"QARM: Quantitative Alignment Multi-Modal Recommendation at Kuaishou. arXiv preprint arXiv:2411.11739","author":"Luo Xinchen","year":"2024","unstructured":"Xinchen Luo, Jiangxia Cao, Tianyu Sun, Jinkai Yu, Rui Huang, Wei Yuan, Hezheng Lin, Yichen Zheng, Shiyao Wang, Qigen Hu, et al. 2024. QARM: Quantitative Alignment Multi-Modal Recommendation at Kuaishou. arXiv preprint arXiv:2411.11739 (2024)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/2487575.2488200"},{"key":"e_1_3_2_1_29_1","volume-title":"MIN: Multi-stage Interactive Network for Multimodal Recommendation. In International Conference on Web Information Systems Engineering. Springer, 191--205","author":"Mo Minghao","year":"2024","unstructured":"Minghao Mo, Weihai Lu, Qixiao Xie, Xiang Lv, Zikai Xiao, Hong Yang, and Yanchun Zhang. 2024. MIN: Multi-stage Interactive Network for Multimodal Recommendation. In International Conference on Web Information Systems Engineering. Springer, 191--205."},{"key":"e_1_3_2_1_30_1","volume-title":"One multimodal plugin enhancing all: CLIP-based pre-training framework enhancing multimodal item representations in recommendation systems. Neurocomputing","author":"Mo Minghao","year":"2025","unstructured":"Minghao Mo, Weihai Lu, Qixiao Xie, Zikai Xiao, Xiang Lv, Hong Yang, and Yanchun Zhang. 2025. One multimodal plugin enhancing all: CLIP-based pre-training framework enhancing multimodal item representations in recommendation systems. Neurocomputing (2025), 130059."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412744"},{"key":"e_1_3_2_1_32_1","volume-title":"International conference on machine learning. PMLR, 8748--8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748--8763."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2010.127"},{"key":"e_1_3_2_1_34_1","volume-title":"Multimodal Representations: Challenges, Approaches and Insights. arXiv preprint arXiv:2407.19467","author":"Sheng Xiang-Rong","year":"2024","unstructured":"Xiang-Rong Sheng, Feifan Yang, Litong Gong, Biao Wang, Zhangming Chan, Yujing Zhang, Yueyao Cheng, Yong-Nan Zhu, Tiezheng Ge, Han Zhu, et al. 2024. Enhancing Taobao Display Advertising with Multimodal Representations: Challenges, Approaches and Insights. arXiv preprint arXiv:2407.19467 (2024)."},{"key":"e_1_3_2_1_35_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_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383313.3412236"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2020.102277"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3124749.3124754"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350875"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591663"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-2262-4_13"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591716"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351034"},{"key":"e_1_3_2_1_44_1","volume-title":"Neural news recommendation with attentive multi-view learning. arXiv preprint arXiv:1907.05576","author":"Wu Chuhan","year":"2019","unstructured":"Chuhan Wu, Fangzhao Wu, Mingxiao An, Jianqiang Huang, Yongfeng Huang, and Xing Xie. 2019. Neural news recommendation with attentive multi-view learning. arXiv preprint arXiv:1907.05576 (2019)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548366"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657719"},{"key":"e_1_3_2_1_47_1","volume-title":"International conference on machine learning. PMLR, 802--810","author":"Yan Ling","year":"2014","unstructured":"Ling Yan, Wu-Jun Li, Gui-Rong Xue, and Dingyi Han. 2014. Coupled group lasso for web-scale ctr prediction in display advertising. In International conference on machine learning. PMLR, 802--810."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-75765-6_35"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657777"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475259"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657825"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015941"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219823"}],"event":{"name":"SIGIR '25: The 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Padua Italy","acronym":"SIGIR '25","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3726302.3729949","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T18:31:59Z","timestamp":1755887519000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3726302.3729949"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,13]]},"references-count":53,"alternative-id":["10.1145\/3726302.3729949","10.1145\/3726302"],"URL":"https:\/\/doi.org\/10.1145\/3726302.3729949","relation":{},"subject":[],"published":{"date-parts":[[2025,7,13]]},"assertion":[{"value":"2025-07-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}