{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T15:49:19Z","timestamp":1781884159072,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":58,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,3,10]],"date-time":"2025-03-10T00:00:00Z","timestamp":1741564800000},"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":[[2025,3,10]]},"DOI":"10.1145\/3701551.3703507","type":"proceedings-article","created":{"date-parts":[[2025,2,26]],"date-time":"2025-02-26T12:33:36Z","timestamp":1740573216000},"page":"782-791","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Teach Me How to Denoise: A Universal Framework for Denoising Multi-modal Recommender Systems via Guided Calibration"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-7656-4333","authenticated-orcid":false,"given":"Hongji","family":"Li","sequence":"first","affiliation":[{"name":"Lanzhou University, Lanzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0486-926X","authenticated-orcid":false,"given":"Hanwen","family":"Du","sequence":"additional","affiliation":[{"name":"The Ohio State University, Columbus, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1290-3604","authenticated-orcid":false,"given":"Youhua","family":"Li","sequence":"additional","affiliation":[{"name":"City University of Hong Kong, HongKong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4759-2042","authenticated-orcid":false,"given":"Junchen","family":"Fu","sequence":"additional","affiliation":[{"name":"University of Glasgow, Glasgow, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6946-9726","authenticated-orcid":false,"given":"Chunxiao","family":"Li","sequence":"additional","affiliation":[{"name":"University of Science and Technoloogy of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-9697-6131","authenticated-orcid":false,"given":"Ziyi","family":"Zhuang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3036-0632","authenticated-orcid":false,"given":"Jiakang","family":"Li","sequence":"additional","affiliation":[{"name":"Rutgers University, New Brunswick, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7606-1475","authenticated-orcid":false,"given":"Yongxin","family":"Ni","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,3,10]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. 2023. GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_2_1","volume-title":"Towards principled methods for training generative adversarial networks. arXiv preprint arXiv:1701.04862","author":"Arjovsky Martin","year":"2017","unstructured":"Martin Arjovsky and L\u00e9on Bottou. 2017. Towards principled methods for training generative adversarial networks. arXiv preprint arXiv:1701.04862 (2017)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080797"},{"key":"e_1_3_2_1_4_1","volume-title":"International conference on machine learning. PMLR, 1597--1607","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. PMLR, 1597--1607."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331254"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611978032.49"},{"key":"e_1_3_2_1_7_1","volume-title":"Sinkhorn distances: Lightspeed computation of optimal transport. Advances in neural information processing systems","author":"Cuturi Marco","year":"2013","unstructured":"Marco Cuturi. 2013. Sinkhorn distances: Lightspeed computation of optimal transport. Advances in neural information processing systems, Vol. 26 (2013)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657725"},{"key":"e_1_3_2_1_9_1","volume-title":"Efficient and Effective Adaptation of Multimodal Foundation Models in Sequential Recommendation. arXiv preprint arXiv:2411.02992","author":"Fu Junchen","year":"2024","unstructured":"Junchen Fu, Xuri Ge, Xin Xin, Alexandros Karatzoglou, Ioannis Arapakis, Kaiwen Zheng, Yongxin Ni, and Joemon M Jose. 2024b. Efficient and Effective Adaptation of Multimodal Foundation Models in Sequential Recommendation. arXiv preprint arXiv:2411.02992 (2024)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3616855.3635805"},{"key":"e_1_3_2_1_11_1","volume-title":"Proceedings of KDD Cup","author":"Gantner Zeno","year":"2012","unstructured":"Zeno Gantner, Lucas Drumond, Christoph Freudenthaler, and Lars Schmidt-Thieme. 2012. Personalized ranking for non-uniformly sampled items. In Proceedings of KDD Cup 2011. PMLR, 231--247."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3532059"},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of the thirteenth international conference on artificial intelligence and statistics","author":"Glorot Xavier","year":"2010","unstructured":"Xavier Glorot and Yoshua Bengio. 2010. Understanding the difficulty of training deep feedforward neural networks. Proceedings of the thirteenth international conference on artificial intelligence and statistics (2010), 249--256."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/1835449.1835484"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.9973"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401063"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/2911451.2911489"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052569"},{"key":"e_1_3_2_1_20_1","volume-title":"Session-based Recommendations with Recurrent Neural Networks. In International Conference on Learning Representations.","author":"Hidasi Bal\u00e1zs","year":"2016","unstructured":"Bal\u00e1zs Hidasi, Alexandros Karatzoglou, Linas Baltrunas, and Domonkos Tikk. 2016. Session-based Recommendations with Recurrent Neural Networks. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_21_1","volume-title":"Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531","author":"Hinton Geoffrey","year":"2015","unstructured":"Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. 2015. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539381"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2008.22"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612091"},{"key":"e_1_3_2_1_25_1","volume-title":"Sequence-level knowledge distillation. arXiv preprint arXiv:1606.07947","author":"Kim Yoon","year":"2016","unstructured":"Yoon Kim and Alexander M Rush. 2016. Sequence-level knowledge distillation. arXiv preprint arXiv:1606.07947 (2016)."},{"key":"e_1_3_2_1_26_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_1_27_1","volume-title":"An Empirical Study of Training ID-Agnostic Multi-modal Sequential Recommenders. arXiv preprint arXiv:2403.17372","author":"Li Youhua","year":"2024","unstructured":"Youhua Li, Hanwen Du, Yongxin Ni, Yuanqi He, Junchen Fu, Xiangyan Liu, and Qi Guo. 2024a. An Empirical Study of Training ID-Agnostic Multi-modal Sequential Recommenders. arXiv preprint arXiv:2403.17372 (2024)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE60146.2024.00380"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766462.2767755"},{"key":"e_1_3_2_1_30_1","volume-title":"A content-driven micro-video recommendation dataset at scale. arXiv preprint arXiv:2309.15379","author":"Ni Yongxin","year":"2023","unstructured":"Yongxin Ni, Yu Cheng, Xiangyan Liu, Junchen Fu, Youhua Li, Xiangnan He, Yongfeng Zhang, and Fajie Yuan. 2023. A content-driven micro-video recommendation dataset at scale. arXiv preprint arXiv:2309.15379 (2023)."},{"key":"e_1_3_2_1_31_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_32_1","volume-title":"Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125","author":"Ramesh Aditya","year":"2022","unstructured":"Aditya Ramesh, Prafulla Dhariwal, Alex Nichol, Casey Chu, and Mark Chen. 2022. Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125, Vol. 1, 2 (2022), 3."},{"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":"BPR: Bayesian personalized ranking from implicit feedback. arXiv preprint arXiv:1205.2618","author":"Rendle Steffen","year":"2012","unstructured":"Steffen Rendle, Christoph Freudenthaler, Zeno Gantner, and Lars Schmidt-Thieme. 2012. BPR: Bayesian personalized ranking from implicit feedback. arXiv preprint arXiv:1205.2618 (2012)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383313.3412488"},{"key":"e_1_3_2_1_36_1","volume-title":"E-commerce recommendation applications. Data mining and knowledge discovery","author":"Schafer J Ben","year":"2001","unstructured":"J Ben Schafer, Joseph A Konstan, and John Riedl. 2001. E-commerce recommendation applications. Data mining and knowledge discovery, Vol. 5 (2001), 115--153."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11784"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357895"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531889"},{"key":"e_1_3_2_1_40_1","unstructured":"Hugo Touvron Thibaut Lavril Gautier Izacard Xavier Martinet Marie-Anne Lachaux Timoth\u00e9e Lacroix Baptiste Rozi\u00e8re Naman Goyal Eric Hambro Faisal Azhar et al. 2023. LLaMa: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_1_41_1","volume-title":"TransRec: Learning Transferable Recommendation from Mixture-of-Modality Feedback. arXiv preprint arXiv:2206.06190","author":"Wang Jie","year":"2022","unstructured":"Jie Wang, Fajie Yuan, Mingyue Cheng, Joemon M Jose, and Chenyun Yu. 2022b. Beibei Kong, Zhijin Wang, Bo Hu, and Zang Li. 2022. TransRec: Learning Transferable Recommendation from Mixture-of-Modality Feedback. arXiv preprint arXiv:2206.06190 (2022)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3437963.3441800"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512202"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599324"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583206"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413556"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351034"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462862"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3494523"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3532027"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591932"},{"key":"e_1_3_2_1_52_1","volume-title":"NineRec: A benchmark dataset suite for evaluating transferable recommendation","author":"Zhang Jiaqi","year":"2024","unstructured":"Jiaqi Zhang, Yu Cheng, Yongxin Ni, Yunzhu Pan, Zheng Yuan, Junchen Fu, Youhua Li, Jie Wang, and Fajie Yuan. 2024. NineRec: A benchmark dataset suite for evaluating transferable recommendation. IEEE Transactions on Pattern Analysis and Machine Intelligence (2024)."},{"key":"e_1_3_2_1_53_1","volume-title":"Proceedings of the ACM International Conference on Multimedia. ACM.","author":"Zhang Jiwei","year":"2017","unstructured":"Jiwei Zhang and Yifan Peng. 2017. Deep Cross-Modal Projection Learning for Image-Text Matching in Multimedia Recommendation Systems. In Proceedings of the ACM International Conference on Multimedia. ACM."},{"key":"e_1_3_2_1_54_1","volume-title":"Advances in Neural Information Processing Systems","volume":"25","author":"Zhen Yan","year":"2012","unstructured":"Yan Zhen and Dit-Yan Yeung. 2012. Co-Regularized Hashing for Multimodal Data. Advances in Neural Information Processing Systems, Vol. 25 (2012)."},{"key":"e_1_3_2_1_55_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. 2023b. A comprehensive survey on multimodal recommender systems: Taxonomy, evaluation, and future directions. arXiv preprint arXiv:2302.04473 (2023)."},{"key":"e_1_3_2_1_56_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. 2023c. Enhancing dyadic relations with homogeneous graphs for multimodal recommendation. arXiv preprint arXiv:2301.12097 (2023)."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611943"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583251"}],"event":{"name":"WSDM '25: The Eighteenth ACM International Conference on Web Search and Data Mining","location":"Hannover Germany","acronym":"WSDM '25","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the Eighteenth ACM International Conference on Web Search and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3701551.3703507","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3701551.3703507","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T09:16:37Z","timestamp":1755767797000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3701551.3703507"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,10]]},"references-count":58,"alternative-id":["10.1145\/3701551.3703507","10.1145\/3701551"],"URL":"https:\/\/doi.org\/10.1145\/3701551.3703507","relation":{},"subject":[],"published":{"date-parts":[[2025,3,10]]},"assertion":[{"value":"2025-03-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}