{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T02:41:05Z","timestamp":1783737665510,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":59,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,10]]},"DOI":"10.1145\/3746252.3761242","type":"proceedings-article","created":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T23:55:33Z","timestamp":1762559733000},"page":"4571-4581","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Frequency-Decoupled Distillation for Efficient Multimodal 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\/0009-0005-7656-4333","authenticated-orcid":false,"given":"Hongji","family":"Li","sequence":"additional","affiliation":[{"name":"Lanzhou University, Lanzhou, 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\/0009-0002-7916-9820","authenticated-orcid":false,"given":"Jiacheng","family":"Liu","sequence":"additional","affiliation":[{"name":"South China Normal University, Guangzhou, China"}],"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\/0009-0006-1290-3604","authenticated-orcid":false,"given":"Youhua","family":"Li","sequence":"additional","affiliation":[{"name":"City University of Hong Kong, Hong Kong, Hong Kong"}],"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":[[2025,11,10]]},"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":"10.1609\/aaai.v35i5.16514"},{"key":"e_1_3_2_1_3_1","unstructured":"Jang Hyun Cho and Bharath Hariharan. 2019. On the efficacy of knowledge distillation. In ICCV."},{"key":"e_1_3_2_1_4_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_5_1","volume-title":"Convolutional neural networks on graphs with fast localized spectral filtering. Advances in neural information processing systems","author":"Defferrard Micha\u00ebl","year":"2016","unstructured":"Micha\u00ebl Defferrard, Xavier Bresson, and Pierre Vandergheynst. 2016. Convolutional neural networks on graphs with fast localized spectral filtering. Advances in neural information processing systems, Vol. 29 (2016)."},{"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","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_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","volume-title":"CROSSAN: Towards Efficient and Effective Adaptation of Multiple Multimodal Foundation Models for Sequential Recommendation. arXiv preprint arXiv:2504.10307","author":"Fu Junchen","year":"2025","unstructured":"Junchen Fu, Yongxin Ni, Joemon M Jose, Ioannis Arapakis, Kaiwen Zheng, Youhua Li, and Xuri Ge. 2025. CROSSAN: Towards Efficient and Effective Adaptation of Multiple Multimodal Foundation Models for Sequential Recommendation. arXiv preprint arXiv:2504.10307 (2025)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2945180"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i8.28688"},{"key":"e_1_3_2_1_13_1","volume-title":"VBPR: visual bayesian personalized ranking from implicit feedback","author":"He Ruining","unstructured":"Ruining He and Julian McAuley. 2016. VBPR: visual bayesian personalized ranking from implicit feedback. In Association for the Advancement of Artificial Intelligence, Vol. 30."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401063"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052569"},{"key":"e_1_3_2_1_16_1","unstructured":"Byeongho Heo Jeesoo Kim Sangdoo Yun Hyojin Park Nojun Kwak and Jin Young Choi. 2019a. A comprehensive overhaul of feature distillation. In ICCV."},{"key":"e_1_3_2_1_17_1","unstructured":"Byeongho Heo Minsik Lee Sangdoo Yun and Jin Young Choi. 2019b. Knowledge transfer via distillation of activation boundaries formed by hidden neurons. In AAAI."},{"key":"e_1_3_2_1_18_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_19_1","volume-title":"Like what you like: Knowledge distill via neuron selectivity transfer. arXiv:1707.01219","author":"Huang Zehao","year":"2017","unstructured":"Zehao Huang and Naiyan Wang. 2017. Like what you like: Knowledge distill via neuron selectivity transfer. arXiv:1707.01219 (2017)."},{"key":"e_1_3_2_1_20_1","unstructured":"Jangho Kim SeongUk Park and Nojun Kwak. 2018. Paraphrasing complex network: Network compression via factor transfer. In NeurIPS."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3701551.3703507"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE60146.2024.00380"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5963"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","unstructured":"Seyed Iman Mirzadeh Mehrdad Farajtabar Ang Li Nir Levine Akihiro Matsukawa and Hassan Ghasemzadeh. 2020b. Improved knowledge distillation via teacher assistant. In AAAI.","DOI":"10.1609\/aaai.v34i04.5963"},{"key":"e_1_3_2_1_25_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_26_1","volume-title":"Spectrum-based Modality Representation Fusion Graph Convolutional Network for Multimodal Recommendation. arXiv preprint arXiv:2412.14978","author":"Ong Rongqing Kenneth","year":"2024","unstructured":"Rongqing Kenneth Ong and Andy WH Khong. 2024. Spectrum-based Modality Representation Fusion Graph Convolutional Network for Multimodal Recommendation. arXiv preprint arXiv:2412.14978 (2024)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"crossref","unstructured":"Wonpyo Park Dongju Kim Yan Lu and Minsu Cho. 2019. Relational knowledge distillation. In CVPR.","DOI":"10.1109\/CVPR.2019.00409"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"Baoyun Peng Xiao Jin Jiaheng Liu Dongsheng Li Yichao Wu Yu Liu Shunfeng Zhou and Zhaoning Zhang. 2019. Correlation congruence for knowledge distillation. In CVPR.","DOI":"10.1109\/ICCV.2019.00511"},{"key":"e_1_3_2_1_29_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_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"e_1_3_2_1_31_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_32_1","volume-title":"Antoine Chassang, Carlo Gatta, and Yoshua Bengio.","author":"Romero Adriana","year":"2015","unstructured":"Adriana Romero, Nicolas Ballas, Samira Ebrahimi Kahou, Antoine Chassang, Carlo Gatta, and Yoshua Bengio. 2015. Fitnets: Hints for thin deep nets. ICLR (2015)."},{"key":"e_1_3_2_1_33_1","volume-title":"The emerging field of signal processing on graphs: Extending high-dimensional data analysis to networks and other irregular domains","author":"Shuman David I","year":"2013","unstructured":"David I Shuman, Sunil K Narang, Pascal Frossard, Antonio Ortega, and Pierre Vandergheynst. 2013. The emerging field of signal processing on graphs: Extending high-dimensional data analysis to networks and other irregular domains. IEEE signal processing magazine, Vol. 30, 3 (2013), 83-98."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00926"},{"key":"e_1_3_2_1_35_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. 2022. Self-supervised Learning for Multimedia Recommendation. Transactions on Multimedia (TMM) (2022)."},{"key":"e_1_3_2_1_36_1","volume-title":"Contrastive representation distillation. arXiv preprint arXiv:1910.10699","author":"Tian Yonglong","year":"2019","unstructured":"Yonglong Tian, Dilip Krishnan, and Phillip Isola. 2019. Contrastive representation distillation. arXiv preprint arXiv:1910.10699 (2019)."},{"key":"e_1_3_2_1_37_1","unstructured":"Yonglong Tian Dilip Krishnan and Phillip Isola. 2020. Contrastive representation distillation. In ICLR."},{"key":"e_1_3_2_1_38_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_39_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_40_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_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3604915.3608807"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413556"},{"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":"International conference on machine learning. PMLR, 6861-6871","author":"Wu Felix","year":"2019","unstructured":"Felix Wu, Amauri Souza, Tianyi Zhang, Christopher Fifty, Tao Yu, and Kilian Weinberger. 2019. Simplifying graph convolutional networks. In International conference on machine learning. PMLR, 6861-6871."},{"key":"e_1_3_2_1_45_1","volume-title":"Graph convolutional networks using heat kernel for semi-supervised learning. arXiv preprint arXiv:2007.16002","author":"Xu Bingbing","year":"2020","unstructured":"Bingbing Xu, Huawei Shen, Qi Cao, Keting Cen, and Xueqi Cheng. 2020. Graph convolutional networks using heat kernel for semi-supervised learning. arXiv preprint arXiv:2007.16002 (2020)."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"crossref","unstructured":"Chenglin Yang Lingxi Xie Chi Su and Alan L Yuille. 2019. Snapshot distillation: Teacher-student optimization in one generation. In CVPR.","DOI":"10.1109\/CVPR.2019.00297"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613915"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591932"},{"key":"e_1_3_2_1_49_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_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3221949"},{"key":"e_1_3_2_1_51_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_52_1","doi-asserted-by":"crossref","unstructured":"Ying Zhang Tao Xiang Timothy M Hospedales and Huchuan Lu. 2018. Deep mutual learning. In CVPR.","DOI":"10.1109\/CVPR.2018.00454"},{"key":"e_1_3_2_1_53_1","volume-title":"Decoupled Knowledge Distillation. arXiv preprint arXiv:2203.08679","author":"Zhao Borui","year":"2022","unstructured":"Borui Zhao, Quan Cui, Renjie Song, Yiyu Qiu, and Jiajun Liang. 2022. Decoupled Knowledge Distillation. arXiv preprint arXiv:2203.08679 (2022)."},{"key":"e_1_3_2_1_54_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. 2023a. A comprehensive survey on multimodal recommender systems: Taxonomy, evaluation, and future directions. arXiv preprint arXiv:2302.04473 (2023)."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.3233\/FAIA230631"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3611380.3628561"},{"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","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."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288775"}],"event":{"name":"CIKM '25: The 34th ACM International Conference on Information and Knowledge Management","location":"Seoul Republic of Korea","acronym":"CIKM '25","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the 34th ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746252.3761242","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T00:01:04Z","timestamp":1765497664000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746252.3761242"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,10]]},"references-count":59,"alternative-id":["10.1145\/3746252.3761242","10.1145\/3746252"],"URL":"https:\/\/doi.org\/10.1145\/3746252.3761242","relation":{},"subject":[],"published":{"date-parts":[[2025,11,10]]},"assertion":[{"value":"2025-11-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}