{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T02:40:12Z","timestamp":1783737612261,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":62,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T00:00:00Z","timestamp":1745280000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,4,22]]},"DOI":"10.1145\/3696410.3714852","type":"proceedings-article","created":{"date-parts":[[2025,5,5]],"date-time":"2025-05-05T16:42:02Z","timestamp":1746463322000},"page":"2464-2475","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Bridging the Gap: Teacher-Assisted Wasserstein Knowledge Distillation for Efficient Multi-Modal Recommendation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-9697-6131","authenticated-orcid":false,"given":"Ziyi","family":"Zhuang","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, 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":"Soochow University, Suzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4580-9467","authenticated-orcid":false,"given":"Hui","family":"Han","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"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, Hong Kong, 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, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9228-1759","authenticated-orcid":false,"given":"Joemon M.","family":"Jose","sequence":"additional","affiliation":[{"name":"University of Glasgow, Glasgow, United Kingdom"}],"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":[[2025,4,22]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"International Conference on Machine Learning. PMLR, 214--223","author":"Arjovsky Martin","year":"2017","unstructured":"Martin Arjovsky, Soumith Chintala, and L\u00e9on Bottou. 2017. Wasserstein generative adversarial networks. In International Conference on Machine Learning. PMLR, 214--223."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3604915.3608857"},{"key":"e_1_3_2_1_3_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_4_1","volume-title":"Sinkhorn Distance Minimization for Knowledge Distillation. arXiv preprint arXiv:2402.17110","author":"Cui Xiao","year":"2024","unstructured":"Xiao Cui, Yulei Qin, Yuting Gao, Enwei Zhang, Zihan Xu, Tong Wu, Ke Li, Xing Sun, Wengang Zhou, and Houqiang Li. 2024. Sinkhorn Distance Minimization for Knowledge Distillation. arXiv preprint arXiv:2402.17110 (2024)."},{"key":"e_1_3_2_1_5_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_6_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, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583529"},{"key":"e_1_3_2_1_8_1","volume-title":"The 22nd International Conference on Artificial Intelligence and Statistics. PMLR, 2681--2690","author":"Feydy Jean","year":"2019","unstructured":"Jean Feydy, Thibault S\u00e9journ\u00e9, Fran\u00e7ois-Xavier Vialard, Shun-ichi Amari, Alain Trouv\u00e9, and Gabriel Peyr\u00e9. 2019. Interpolating between optimal transport and mmd using sinkhorn divergences. In The 22nd International Conference on Artificial Intelligence and Statistics. PMLR, 2681--2690."},{"key":"e_1_3_2_1_9_1","volume-title":"Learning with a Wasserstein loss. Advances in neural information processing systems","author":"Frogner Charlie","year":"2015","unstructured":"Charlie Frogner, Chiyuan Zhang, Hossein Mobahi, Mauricio Araya, and Tomaso A Poggio. 2015. Learning with a Wasserstein loss. Advances in neural information processing systems, Vol. 28 (2015)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657725"},{"key":"e_1_3_2_1_11_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_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3616855.3635805"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i8.28688"},{"key":"e_1_3_2_1_14_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Hao Zhiwei","year":"2024","unstructured":"Zhiwei Hao, Jianyuan Guo, Kai Han, Yehui Tang, Han Hu, Yunhe Wang, and Chang Xu. 2024. One-for-all: Bridge the gap between heterogeneous architectures in knowledge distillation. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"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":"10.1145\/2872427.2883037"},{"key":"e_1_3_2_1_17_1","volume-title":"VBPR: visual bayesian personalized ranking from implicit feedback","author":"He Ruining","unstructured":"Ruining He and Julian McAuley. 2016b. VBPR: visual bayesian personalized ranking from implicit feedback. In Association for the Advancement of Artificial Intelligence, Vol. 30."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401063"},{"key":"e_1_3_2_1_19_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_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3614775"},{"key":"e_1_3_2_1_21_1","first-page":"33716","article-title":"Knowledge distillation from a stronger teacher","volume":"35","author":"Huang Tao","year":"2022","unstructured":"Tao Huang, Shan You, Fei Wang, Chen Qian, and Chang Xu. 2022. Knowledge distillation from a stronger teacher. Advances in Neural Information Processing Systems, Vol. 35 (2022), 33716--33727.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_22_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Huang Tao","year":"2024","unstructured":"Tao Huang, Yuan Zhang, Mingkai Zheng, Shan You, Fei Wang, Chen Qian, and Chang Xu. 2024. Knowledge diffusion for distillation. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_23_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Conference of the North American Chapter of the Association for Computational Linguistics. 4171--4186","author":"Ming-Wei Chang Jacob Devlin","year":"2019","unstructured":"Jacob Devlin Ming-Wei Chang Kenton and Lee Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Conference of the North American Chapter of the Association for Computational Linguistics. 4171--4186."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403226"},{"key":"e_1_3_2_1_25_1","volume-title":"Markov chains and mixing times","author":"Levin David A","unstructured":"David A Levin and Yuval Peres. 2017. Markov chains and mixing times. Vol. 107. American Mathematical Soc."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE60146.2024.00380"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657807"},{"key":"e_1_3_2_1_28_1","volume-title":"Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)."},{"key":"e_1_3_2_1_29_1","volume-title":"Image-based recommendations on styles and substitutes","author":"McAuley Julian","unstructured":"Julian McAuley, Christopher Targett, Qinfeng Shi, and Anton Van Den Hengel. 2015. Image-based recommendations on styles and substitutes. In ACM Special Interest Group on Information Retrieval. 43--52."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5963"},{"key":"e_1_3_2_1_31_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_32_1","volume-title":"Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748","author":"van den Oord Aaron","year":"2018","unstructured":"Aaron van den Oord, Yazhe Li, and Oriol Vinyals. 2018. Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)."},{"key":"e_1_3_2_1_33_1","volume-title":"Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. 2019. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00752"},{"key":"e_1_3_2_1_35_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_36_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"e_1_3_2_1_37_1","volume-title":"BPR: Bayesian personalized ranking from implicit feedback. In UAI.","author":"Rendle Steffen","year":"2012","unstructured":"Steffen Rendle, Christoph Freudenthaler, Zeno Gantner, and Lars Schmidt-Thieme. 2012. BPR: Bayesian personalized ranking from implicit feedback. In UAI."},{"key":"e_1_3_2_1_38_1","first-page":"58","article-title":"Optimal transport for applied mathematicians. Birk\u00e4user","volume":"55","author":"Santambrogio Filippo","year":"2015","unstructured":"Filippo Santambrogio. 2015. Optimal transport for applied mathematicians. Birk\u00e4user, NY, Vol. 55, 58--63 (2015), 94.","journal-title":"NY"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00926"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512003"},{"key":"e_1_3_2_1_41_1","volume-title":"Self-supervised Learning for Multimedia Recommendation. Transactions on Multimedia (TMM)","author":"Tao Zhulin","year":"2022","unstructured":"Zhulin Tao, Xiaohao Liu, Yewei Xia, Xiang Wang, Lifang Yang, Xianglin Huang, and Tat-Seng Chua. 2022b. Self-supervised Learning for Multimedia Recommendation. Transactions on Multimedia (TMM) (2022)."},{"key":"e_1_3_2_1_42_1","first-page":"64","article-title":"Markov processes over denumerable products of spaces, describing large systems of automata","volume":"5","author":"Vaserstein Leonid Nisonovich","year":"1969","unstructured":"Leonid Nisonovich Vaserstein. 1969. Markov processes over denumerable products of spaces, describing large systems of automata. Problemy Peredachi Informatsii, Vol. 5, 3 (1969), 64--72.","journal-title":"Problemy Peredachi Informatsii"},{"key":"e_1_3_2_1_43_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Viallard Paul","year":"2024","unstructured":"Paul Viallard, Maxime Haddouche, Umut Simsekli, and Benjamin Guedj. 2024. Learning via Wasserstein-based high probability generalisation bounds. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3138298"},{"key":"e_1_3_2_1_45_1","volume-title":"Neural Graph Collaborative Filtering","author":"Wang Xiang","unstructured":"Xiang Wang, Xiangnan He, Meng Wang, Fuli Feng, and Tat-Seng Chua. 2019. Neural Graph Collaborative Filtering. In ACM Special Interest Group on Information Retrieval."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645359"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3604915.3608807"},{"key":"e_1_3_2_1_48_1","volume-title":"Hierarchical user intent graph network for multimedia recommendation. Transactions on Multimedia (TMM)","author":"Wei Yinwei","year":"2021","unstructured":"Yinwei Wei, Xiang Wang, Xiangnan He, Liqiang Nie, Yong Rui, and Tat-Seng Chua. 2021a. Hierarchical user intent graph network for multimedia recommendation. Transactions on Multimedia (TMM) (2021)."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475665"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413556"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351034"},{"key":"e_1_3_2_1_52_1","volume-title":"f-Divergence Minimization for Sequence-Level Knowledge Distillation. arXiv preprint arXiv:2307.15190","author":"Wen Yuqiao","year":"2023","unstructured":"Yuqiao Wen, Zichao Li, Wenyu Du, and Lili Mou. 2023. f-Divergence Minimization for Sequence-Level Knowledge Distillation. arXiv preprint arXiv:2307.15190 (2023)."},{"key":"e_1_3_2_1_53_1","volume-title":"Mm-rec: multimodal news recommendation. arXiv preprint arXiv:2104.07407","author":"Wu Chuhan","year":"2021","unstructured":"Chuhan Wu, Fangzhao Wu, Tao Qi, and Yongfeng Huang. 2021. Mm-rec: multimodal news recommendation. arXiv preprint arXiv:2104.07407 (2021)."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475514"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613915"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591932"},{"key":"e_1_3_2_1_57_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_58_1","volume-title":"Mining Latent Structures for Multimedia Recommendation. In ACM Multimedia Conference. 3872--3880","author":"Zhang Jinghao","year":"2021","unstructured":"Jinghao Zhang, Yanqiao Zhu, Qiang Liu, Shu Wu, Liang Wang, et al. 2021b. Mining Latent Structures for Multimedia Recommendation. In ACM Multimedia Conference. 3872--3880."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3221949"},{"key":"e_1_3_2_1_60_1","volume-title":"Graph-less neural networks: Teaching old mlps new tricks via distillation. arXiv preprint arXiv:2110.08727","author":"Zhang Shichang","year":"2021","unstructured":"Shichang Zhang, Yozen Liu, Yizhou Sun, and Neil Shah. 2021a. Graph-less neural networks: Teaching old mlps new tricks via distillation. arXiv preprint arXiv:2110.08727 (2021)."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611943"},{"key":"e_1_3_2_1_62_1","volume-title":"ACM International World Wide Web Conference.","author":"Zhou Xin","year":"2022","unstructured":"Xin Zhou, Hongyu Zhou, Yong Liu, Zhiwei Zeng, Chunyan Miao, Pengwei Wang, Yuan You, and Feijun Jiang. 2022. Bootstrap latent representations for multi-modal recommendation. In ACM International World Wide Web Conference."}],"event":{"name":"WWW '25: The ACM Web Conference 2025","location":"Sydney NSW Australia","acronym":"WWW '25","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM on Web Conference 2025"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3696410.3714852","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3696410.3714852","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:42Z","timestamp":1750295922000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3696410.3714852"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,22]]},"references-count":62,"alternative-id":["10.1145\/3696410.3714852","10.1145\/3696410"],"URL":"https:\/\/doi.org\/10.1145\/3696410.3714852","relation":{},"subject":[],"published":{"date-parts":[[2025,4,22]]},"assertion":[{"value":"2025-04-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}