{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T19:02:28Z","timestamp":1764788548628,"version":"3.46.0"},"reference-count":74,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Major Technological Innovation Projects for 2030","award":["2021ZD0111801"],"award-info":[{"award-number":["2021ZD0111801"]}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018AAA0101204","2018AAA0101200"],"award-info":[{"award-number":["2018AAA0101204","2018AAA0101200"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172384"],"award-info":[{"award-number":["62172384"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput. Soc. Syst."],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1109\/tcss.2025.3555653","type":"journal-article","created":{"date-parts":[[2025,4,10]],"date-time":"2025-04-10T13:19:00Z","timestamp":1744291140000},"page":"4517-4531","source":"Crossref","is-referenced-by-count":0,"title":["Modality-Disentangled Feature Extraction via Knowledge Distillation in Multimodal Recommendation Systems"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1207-4472","authenticated-orcid":false,"given":"Haibing","family":"Hu","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4989-1064","authenticated-orcid":false,"given":"Yangyi","family":"Xie","sequence":"additional","affiliation":[{"name":"Industrial Field, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3507-9607","authenticated-orcid":false,"given":"Defu","family":"Lian","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6302-5366","authenticated-orcid":false,"given":"Kai","family":"Han","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Soochow University, Suzhou, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3682076"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583439"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939673"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401063"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052569"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3158317"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3532075"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1345448.1345465"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2024.3354315"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2024.3411043"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2020.3023155"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/tcss.2024.3517164"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2766462.2767755"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.3040772"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.9973"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210083"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052639"},{"key":"ref18","first-page":"7149","article-title":"Disentangled multimodal representation learning for recommendation","volume-title":"IEEE Trans. Multimedia","volume":"25","author":"Liu","year":"2022"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350953"},{"article-title":"Generative recommendation: Towards next-generation recommender paradigm","year":"2023","author":"Wang","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512079"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611886"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583251"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413556"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2024.3378454"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2023.3276273"},{"key":"ref27","article-title":"Surrogate modeling of pantograph-catenary system interactions","volume-title":"Mech. Syst. Signal Process.","volume":"224","author":"Cheng","year":"2025"},{"key":"ref28","article-title":"An improved envelope spectrum via candidate fault frequency optimization-gram for bearing fault diagnosis","volume-title":"J. Sound Vib.","volume":"523","author":"Cheng","year":"2022"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-66971-2_1"},{"key":"ref30","article-title":"A product envelope spectrum generated from spectral correlation\/coherence for railway axle-box bearing fault diagnosis","volume-title":"Mech. Syst. Signal Process.","volume":"225","author":"Chen","year":"2025"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3132847.3132892"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3344657"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3354910"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3274759"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654902"},{"key":"ref36","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","volume-title":"Proc. 32nd Int. Conf. Mach. Learn., ser. Proc. Mach. Learn. Res.","volume":"37","author":"Xu","year":"2015"},{"article-title":"Very deep convolutional networks for large-scale image recognition","year":"2014","author":"Simonyan","key":"ref37"},{"key":"ref38","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. North Amer. Chapter Assoc. Comput. Linguistics","author":"Devlin","year":"2019"},{"key":"ref39","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/D19-1514","article-title":"LXMERT: Learning cross-modality encoder representations from transformers","volume-title":"Proc. Conf. Empirical Methods Nat. Lang. Process.","author":"Tan","year":"2019"},{"issue":"12","key":"ref40","first-page":"10790","article-title":"Learning modality-specific representations with self-supervised multi-task learning for multimodal sentiment analysis","volume-title":"Proc. AAAI Conf. Artif. Intell.","volume":"35","author":"Yu","year":"2021"},{"issue":"2","key":"ref41","first-page":"423","article-title":"Multimodal machine learning: A survey and taxonomy","volume-title":"IEEE Trans. Pattern Anal. Mach. Intell.","volume":"41","author":"Baltru\u0161aitis","year":"2019"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2024.3377728"},{"issue":"0888\u20133270","key":"ref43","first-page":"12026","article-title":"Probability distributions and typical sparsity measures of hilbert transform-based generalized envelopes and their application to machine condition monitoring","volume-title":"Mech. Syst. Signal Process.","volume":"224","author":"Chen","year":"2025"},{"key":"ref44","doi-asserted-by":"crossref","DOI":"10.3115\/v1\/N15-1016","article-title":"Combining language and vision with a multimodal skip-gram model","volume-title":"Proc. North Amer. Chapter Assoc. Comput. Linguistics","author":"Lazaridou","year":"2015"},{"key":"ref45","article-title":"Multimodal deep learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ngiam","year":"2011"},{"key":"ref46","doi-asserted-by":"crossref","DOI":"10.1145\/2647868.2654931","article-title":"Exploring inter-feature and inter-class relationships with deep neural networks for video classification","volume-title":"Proc. 22nd ACM Int. Conf. Multimedia","author":"Wu","year":"2014"},{"key":"ref47","doi-asserted-by":"crossref","DOI":"10.24963\/ijcai.2018\/365","article-title":"Cross-modal bidirectional translation via reinforcement learning","volume-title":"Proc. Int. Joint Conf. Artif. Intell.","author":"Qi","year":"2018"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2015.7298966"},{"key":"ref49","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-01219-9_11","article-title":"Multimodal unsupervised image-to-image translation","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Huang","year":"2018"},{"issue":"1066\u20138888","key":"ref50","first-page":"325","article-title":"Unified route representation learning for multi-modal transportation recommendation with spatiotemporal pre-training","volume-title":"VLDB J.","volume":"32","author":"Liu","year":"2022"},{"key":"ref51","doi-asserted-by":"crossref","DOI":"10.1145\/3331184.3331254","article-title":"Personalized fashion recommendation with visual explanations based on multimodal attention network: Towards visually explainable recommendation","volume-title":"Proc. 42nd Int. ACM SIGIR Conf. Res. Develop. Inf. Retrieval","author":"Chen","year":"2019"},{"key":"ref52","doi-asserted-by":"crossref","DOI":"10.1145\/3343031.3351034","article-title":"Mmgcn: Multi-modal graph convolution network for personalized recommendation of micro-video","volume-title":"Proc. 27th ACM Int. Conf. Multimedia","author":"Wei","year":"2019"},{"article-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer","year":"2016","author":"Zagoruyko","key":"ref53"},{"article-title":"Distilling the knowledge in a neural network","year":"2015","author":"Hinton","key":"ref54"},{"key":"ref55","first-page":"9155","article-title":"Variational information distillation for knowledge transfer","volume-title":"in Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Ahn","year":"2019"},{"article-title":"Improved feature distillation via projector ensemble","year":"2022","author":"Chen","key":"ref56"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2024.3402270"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3703458"},{"key":"ref59","article-title":"Privacy-preserving knowledge distillation in latency-critical federated task offloading for consumer IoT networks","volume-title":"IEEE Trans. Consum. Electron.","author":"Chen","year":"2024"},{"article-title":"Fitnets: Hints for thin deep nets","year":"2014","author":"Romero","key":"ref60"},{"article-title":"Contrastive representation distillation","year":"2019","author":"Tian","key":"ref61"},{"key":"ref62","doi-asserted-by":"crossref","DOI":"10.1145\/3340531.3412005","article-title":"DE-RRD: A knowledge distillation framework for recommender system","volume-title":"Proc. 29th ACM Int. Conf. Inf. Knowl. Manage.","author":"Kang","year":"2020"},{"key":"ref63","doi-asserted-by":"crossref","DOI":"10.1145\/3219819.3220021","article-title":"Ranking distillation: Learning compact ranking models with high performance for recommender system","volume-title":"Proc. 24th ACM SIGKDD Int. Conf. Knowl. Discovery Data Mining","author":"Tang","year":"2018"},{"key":"ref64","first-page":"369","article-title":"Collaborative distillation for top-n recommendation","volume-title":"Proc. IEEE Int. Conf. Data Mining (ICDM)","author":"Lee","year":"2019"},{"article-title":"Unsupervised learning of visual features by contrasting cluster assignments","year":"2020","author":"Caron","key":"ref65"},{"article-title":"A simple framework for contrastive learning of visual representations","year":"2020","author":"Chen","key":"ref66"},{"key":"ref67","article-title":"Learning word embeddings efficiently with noise-contrastive estimation","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Mnih","year":"2013"},{"key":"ref68","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2020.emnlp-main.124","article-title":"An unsupervised sentence embedding method by mutual information maximization","volume-title":"Proc. Conf. Empirical Methods Nat. Lang. Process.","author":"Zhang","year":"2020"},{"article-title":"Contrastive pre-training for sequential recommendation","year":"2020","author":"Xie","key":"ref69"},{"key":"ref70","article-title":"Self-supervised learning for large-scale item recommendations","volume-title":"Proc. 30th ACM Int. Conf. Inf. Knowl. Manage.","author":"Yao","year":"2020"},{"key":"ref71","doi-asserted-by":"crossref","DOI":"10.1145\/2507157.2507163","article-title":"Hidden factors and hidden topics: understanding rating dimensions with review text","volume-title":"Proc. 7th ACM Conf. Recommender Syst.","author":"McAuley","year":"2013"},{"key":"ref72","doi-asserted-by":"crossref","DOI":"10.1145\/2806416.2806504","article-title":"Trirank: Review-aware explainable recommendation by modeling aspects","volume-title":"Proc. 24th ACM Int. Conf. Inf. Knowl. Manage.","author":"He","year":"2015"},{"key":"ref73","doi-asserted-by":"crossref","DOI":"10.1145\/3331184.3331267","article-title":"Neural graph collaborative filtering","volume-title":"Proc. 42nd Int. ACM SIGIR Conf. Res. Develop. Inf. Retrieval","author":"Wang","year":"2019"},{"key":"ref74","doi-asserted-by":"crossref","DOI":"10.1145\/3397271.3401137","article-title":"Disentangled graph collaborative filtering","volume-title":"Proc. 43rd Int. ACM SIGIR Conf. Res. Develop. Inf. Retrieval","author":"Wang","year":"2020"}],"container-title":["IEEE Transactions on Computational Social Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6570650\/11272985\/10960660.pdf?arnumber=10960660","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T18:44:22Z","timestamp":1764787462000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10960660\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":74,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tcss.2025.3555653","relation":{},"ISSN":["2329-924X","2373-7476"],"issn-type":[{"type":"electronic","value":"2329-924X"},{"type":"electronic","value":"2373-7476"}],"subject":[],"published":{"date-parts":[[2025,12]]}}}