{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T19:16:07Z","timestamp":1778786167206,"version":"3.51.4"},"reference-count":74,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Hong Kong UGC General Research Fund","award":["17203320"],"award-info":[{"award-number":["17203320"]}]},{"name":"Hong Kong UGC General Research Fund","award":["17209822"],"award-info":[{"award-number":["17209822"]}]},{"name":"HKU-SCF FinTech Academy"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Knowl. Data Eng."],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1109\/tkde.2025.3604242","type":"journal-article","created":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T17:34:03Z","timestamp":1757439243000},"page":"6406-6419","source":"Crossref","is-referenced-by-count":4,"title":["Enhancing Robustness and Generalization Capability for Multimodal Recommender Systems via Sharpness-Aware Minimization"],"prefix":"10.1109","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-7876-3740","authenticated-orcid":false,"given":"Jinfeng","family":"Xu","sequence":"first","affiliation":[{"name":"Department of Electrical and Electronic Engineering, University of Hong Kong, Pok Fu Lam, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5779-3523","authenticated-orcid":false,"given":"Zheyu","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, Hong Kong Polytechnic University, Hung Hom, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6749-5442","authenticated-orcid":false,"given":"Jinze","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, University of Hong Kong, Pok Fu Lam, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1638-9623","authenticated-orcid":false,"given":"Shuo","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, University of Hong Kong, Pok Fu Lam, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1717-5785","authenticated-orcid":false,"given":"Wei","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Engineering, Shenzhen MSU-BIT University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4952-699X","authenticated-orcid":false,"given":"Xiping","family":"Hu","sequence":"additional","affiliation":[{"name":"Department of Engineering, Shenzhen MSU-BIT University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Raymond Chi-Wing","family":"Wong","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3454-8731","authenticated-orcid":false,"given":"Edith C. H.","family":"Ngai","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, University of Hong Kong, Pok Fu Lam, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3285029"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2024.3411875"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3679697"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3711896.3737042"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.9973"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351034"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413556"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475259"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611943"},{"issue":"95","key":"ref10","first-page":"1","article-title":"Cornac: A comparative framework for multimodal recommender systems","volume":"21","author":"Salah","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref11","article-title":"A comprehensive survey on multimodal recommender systems: Taxonomy, evaluation, and future directions","author":"Zhou","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2019.2893638"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462914"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2887018"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371841"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645553"},{"key":"ref17","first-page":"5905","article-title":"ASAM: Adaptive sharpness-aware minimization for scale-invariant learning of deep neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kwon"},{"key":"ref18","article-title":"Sharpness-aware minimization for efficiently improving generalization","author":"Foret","year":"2020"},{"key":"ref19","first-page":"30950","article-title":"Make sharpness-aware minimization stronger: A sparsified perturbation approach","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Mi"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401063"},{"key":"ref21","article-title":"FourierKAN-GCF: Fourier Kolmogorov-Arnold network\u2013an effective and efficient feature transformation for graph collaborative filtering","author":"Xu","year":"2024"},{"key":"ref22","article-title":"BPR: Bayesian personalized ranking from implicit feedback","author":"Rendle","year":"2012"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3187556"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583251"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i12.33408"},{"key":"ref26","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref27","first-page":"2874","article-title":"On large-batch training for deep learning: Generalization gap and sharp minima","volume-title":"Proc. 5th Int. Conf. Learn. Representations","author":"Keskar"},{"key":"ref28","article-title":"Computing nonvacuous generalization bounds for deep (stochastic) neural networks with many more parameters than training data","author":"Dziugaite","year":"2017"},{"key":"ref29","first-page":"529","article-title":"Simplifying neural nets by discovering flat minima","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Hochreiter"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/168304.168306"},{"key":"ref31","article-title":"Fantastic generalization measures and where to find them","author":"Jiang","year":"2019"},{"key":"ref32","article-title":"A survey on multimodal recommender systems: Recent advances and future directions","author":"Xu","year":"2025"},{"key":"ref33","article-title":"Normalization layers are all that sharpness-aware minimization needs","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Mueller"},{"key":"ref34","first-page":"639","article-title":"Towards understanding sharpness-aware minimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Andriushchenko"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00538"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1137\/120880811"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46128-1_50"},{"key":"ref38","first-page":"26982","article-title":"Penalizing gradient norm for efficiently improving generalization in deep learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhao"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/2766462.2767755"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3611380.3628561"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i8.28688"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3138298"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.3233\/faia230631"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331267"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE55515.2023.00100"},{"key":"ref46","article-title":"The dawn of LMMs: Preliminary explorations with GPT-4V (ision)","author":"Yang","year":"2023"},{"key":"ref47","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5917"},{"key":"ref49","first-page":"11148","article-title":"Fisher SAM: Information geometry and sharpness aware minimisation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.31390\/gradschool_dissertations.4601"},{"key":"ref51","first-page":"2121","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"Duchi","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-35289-8_25"},{"key":"ref53","first-page":"1139","article-title":"On the importance of initialization and momentum in deep learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sutskever"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3298689.3346987"},{"key":"ref55","article-title":"Integrating large language models into recommendation via mutual augmentation and adaptive aggregation","author":"Luo","year":"2024"},{"key":"ref56","article-title":"Large language model interaction simulator for cold-start item recommendation","author":"Huang","year":"2024"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3616855.3635853"},{"key":"ref58","first-page":"6391","article-title":"Visualizing the loss landscape of neural nets","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331254"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313513"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613915"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3729927"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3651169"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681498"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.1.1"},{"key":"ref66","first-page":"2549","article-title":"Asymmetric valleys: Beyond sharp and flat local minima","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"He"},{"key":"ref67","first-page":"6747","article-title":"Overcoming catastrophic forgetting in incremental few-shot learning by finding flat minima","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Shi"},{"key":"ref68","first-page":"2553","article-title":"Surrogate gap minimization improves sharpness-aware training","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhuang"},{"key":"ref69","article-title":"Enhancing sharpness-aware optimization through variance suppression","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref70","first-page":"9703","article-title":"Efficient sharpness-aware minimization for improved training of neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Du"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01204"},{"key":"ref72","first-page":"23439","article-title":"Sharpness-aware training for free","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Du"},{"key":"ref73","first-page":"1895","article-title":"Sub-sampled cubic regularization for non-convex optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kohler"},{"key":"ref74","first-page":"5956","article-title":"Escaping saddle points with adaptive gradient methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Staib"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/69\/11197180\/11154965.pdf?arnumber=11154965","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:55:27Z","timestamp":1760032527000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11154965\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":74,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tkde.2025.3604242","relation":{},"ISSN":["1041-4347","1558-2191","2326-3865"],"issn-type":[{"value":"1041-4347","type":"print"},{"value":"1558-2191","type":"electronic"},{"value":"2326-3865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11]]}}}