{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T14:30:06Z","timestamp":1781879406767,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":67,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"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":[[2024,5,13]]},"DOI":"10.1145\/3589334.3645553","type":"proceedings-article","created":{"date-parts":[[2024,5,8]],"date-time":"2024-05-08T07:08:13Z","timestamp":1715152093000},"page":"3700-3711","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":13,"title":["Mirror Gradient: Towards Robust Multimodal Recommender Systems via Exploring Flat Local Minima"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3082-7351","authenticated-orcid":false,"given":"Shanshan","family":"Zhong","sequence":"first","affiliation":[{"name":"Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8422-2898","authenticated-orcid":false,"given":"Zhongzhan","family":"Huang","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5457-9324","authenticated-orcid":false,"given":"Daifeng","family":"Li","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4819-4679","authenticated-orcid":false,"given":"Wushao","family":"Wen","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0663-199X","authenticated-orcid":false,"given":"Jinghui","family":"Qin","sequence":"additional","affiliation":[{"name":"Guangdong University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2248-3755","authenticated-orcid":false,"given":"Liang","family":"Lin","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,5,13]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41568-021-00408-3"},{"key":"e_1_3_2_2_2_1","volume-title":"Neural Networks: Tricks of the Trade","author":"Bottou L\u00e9on","unstructured":"L\u00e9on Bottou. 2012. Stochastic gradient descent tricks. In Neural Networks: Tricks of the Trade: Second Edition. Springer, 421--436."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3298689.3346987"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3522672"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3439729"},{"key":"e_1_3_2_2_6_1","volume-title":"Dherin","author":"Benoit","year":"2021","unstructured":"Benoit et al Dherin. 2021. The Geometric Occam's Razor Implicit in Deep Learning. arXiv preprint arXiv:2111.15090 (2021)."},{"key":"e_1_3_2_2_7_1","volume-title":"Liangli Zhen, Rick Siow Mong Goh, and Vincent YF Tan.","author":"Du Jiawei","year":"2021","unstructured":"Jiawei Du, Hanshu Yan, Jiashi Feng, Joey Tianyi Zhou, Liangli Zhen, Rick Siow Mong Goh, and Vincent YF Tan. 2021. Efficient sharpness-aware minimization for improved training of neural networks. arXiv preprint arXiv:2110.03141 (2021)."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2887018"},{"key":"e_1_3_2_2_9_1","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"Duchi John","year":"2011","unstructured":"John Duchi, Elad Hazan, and Yoram Singer. 2011. Adaptive subgradient methods for online learning and stochastic optimization. Journal of machine learning research 12, 7 (2011).","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_2_10_1","volume-title":"Sharpness-aware minimization for efficiently improving generalization. arXiv preprint arXiv:2010.01412","author":"Foret Pierre","year":"2020","unstructured":"Pierre Foret, Ariel Kleiner, Hossein Mobahi, and Behnam Neyshabur. 2020. Sharpness-aware minimization for efficiently improving generalization. arXiv preprint arXiv:2010.01412 (2020)."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3488560.3501396"},{"key":"e_1_3_2_2_12_1","volume-title":"Generating sequences with recurrent neural networks. arXiv preprint arXiv:1308.0850","author":"Graves Alex","year":"2013","unstructured":"Alex Graves. 2013. Generating sequences with recurrent neural networks. arXiv preprint arXiv:1308.0850 (2013)."},{"key":"e_1_3_2_2_13_1","volume-title":"Dynamically Expandable Graph Convolution for Streaming Recommendation. arXiv preprint arXiv:2303.11700","author":"He Bowei","year":"2023","unstructured":"Bowei He, Xu He, Yingxue Zhang, Ruiming Tang, and Chen Ma. 2023. Dynamically Expandable Graph Convolution for Streaming Recommendation. arXiv preprint arXiv:2303.11700 (2023)."},{"key":"e_1_3_2_2_14_1","volume-title":"Asymmetric valleys: Beyond sharp and flat local minima. Advances in neural information processing systems 32","author":"He Haowei","year":"2019","unstructured":"Haowei He, Gao Huang, and Yang Yuan. 2019. Asymmetric valleys: Beyond sharp and flat local minima. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.9973"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86380-7_1"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401063"},{"key":"e_1_3_2_2_18_1","volume-title":"Simplifying neural nets by discovering flat minima. Advances in neural information processing systems 7","author":"Hochreiter Sepp","year":"1994","unstructured":"Sepp Hochreiter and J\u00fcrgen Schmidhuber. 1994. Simplifying neural nets by discovering flat minima. Advances in neural information processing systems 7 (1994)."},{"key":"e_1_3_2_2_19_1","volume-title":"Flat minima. Neural computation 9, 1","author":"Hochreiter Sepp","year":"1997","unstructured":"Sepp Hochreiter and J\u00fcrgen Schmidhuber. 1997. Flat minima. Neural computation 9, 1 (1997), 1--42."},{"key":"e_1_3_2_2_20_1","volume-title":"AlterSGD: Finding Flat Minima for Continual Learning by Alternative Training. arXiv preprint arXiv:2107.05804","author":"Huang Zhongzhan","year":"2021","unstructured":"Zhongzhan Huang, Mingfu Liang, Senwei Liang, and Wei He. 2021. AlterSGD: Finding Flat Minima for Continual Learning by Alternative Training. arXiv preprint arXiv:2107.05804 (2021)."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00136"},{"key":"e_1_3_2_2_22_1","volume-title":"Layer-wise shared attention network on dynamical system perspective. arXiv preprint arXiv:2210.16101","author":"Huang Zhongzhan","year":"2022","unstructured":"Zhongzhan Huang, Senwei Liang, Mingfu Liang,Weiling He, and Liang Lin. 2022. Layer-wise shared attention network on dynamical system perspective. arXiv preprint arXiv:2210.16101 (2022)."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5842"},{"key":"e_1_3_2_2_24_1","first-page":"16305","article-title":"Rethinking the pruning criteria for convolutional neural network","volume":"34","author":"Huang Zhongzhan","year":"2021","unstructured":"Zhongzhan Huang, Wenqi Shao, Xinjiang Wang, Liang Lin, and Ping Luo. 2021. Rethinking the pruning criteria for convolutional neural network. Advances in Neural Information Processing Systems 34 (2021), 16305--16318.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_25_1","volume-title":"Scalelong: Towards more stable training of diffusion model via scaling network long skip connection. Advances in Neural Information Processing Systems 36","author":"Huang Zhongzhan","year":"2024","unstructured":"Zhongzhan Huang, Pan Zhou, Shuicheng Yan, and Liang Lin. 2024. Scalelong: Towards more stable training of diffusion model via scaling network long skip connection. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_2_2_26_1","first-page":"16577","article-title":"When do flat minima optimizers work","volume":"35","author":"Kaddour Jean","year":"2022","unstructured":"Jean Kaddour, Linqing Liu, Ricardo Silva, and Matt J Kusner. 2022. When do flat minima optimizers work? Advances in Neural Information Processing Systems 35 (2022), 16577--16595.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_27_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_2_28_1","volume-title":"International Conference on Machine Learning. PMLR, 5905-- 5914","author":"Kwon Jungmin","year":"2021","unstructured":"Jungmin Kwon, Jeongseop Kim, Hyunseo Park, and In Kwon Choi. 2021. Asam: Adaptive sharpness-aware minimization for scale-invariant learning of deep neural networks. In International Conference on Machine Learning. PMLR, 5905-- 5914."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/1352793.1352837"},{"key":"e_1_3_2_2_30_1","volume-title":"Visualizing the loss landscape of neural nets. Advances in neural information processing systems 31","author":"Li Hao","year":"2018","unstructured":"Hao Li, Zheng Xu, Gavin Taylor, Christoph Studer, and Tom Goldstein. 2018. Visualizing the loss landscape of neural nets. Advances in neural information processing systems 31 (2018)."},{"key":"e_1_3_2_2_31_1","volume-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597 (2023)."},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371841"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5917"},{"key":"e_1_3_2_2_34_1","unstructured":"Daniele Malitesta Giandomenico Cornacchia Claudio Pomo and Tommaso Di Noia. 2023. Disentangling the Performance Puzzle of Multimodal-aware Recommender Systems. In EvalRS@ KDD (CEURWorkshop Proceedings Vol. 3450). CEUR-WS. org."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766462.2767755"},{"key":"e_1_3_2_2_36_1","first-page":"30950","article-title":"Make sharpness-aware minimization stronger: A sparsified perturbation approach","volume":"35","author":"Mi Peng","year":"2022","unstructured":"Peng Mi, Li Shen, Tianhe Ren, Yiyi Zhou, Xiaoshuai Sun, Rongrong Ji, and Dacheng Tao. 2022. Make sharpness-aware minimization stronger: A sparsified perturbation approach. Advances in Neural Information Processing Systems 35 (2022), 30950--30962.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2021.09.006"},{"key":"e_1_3_2_2_38_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_2_39_1","doi-asserted-by":"publisher","DOI":"10.5555\/3455716.3455811"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/564376.564421"},{"key":"e_1_3_2_2_41_1","volume-title":"Overcoming catastrophic forgetting in incremental few-shot learning by finding flat minima. Advances in neural information processing systems 34","author":"Shi Guangyuan","year":"2021","unstructured":"Guangyuan Shi, Jiaxin Chen,Wenlong Zhang, Li-Ming Zhan, and Xiao-MingWu. 2021. Overcoming catastrophic forgetting in incremental few-shot learning by finding flat minima. Advances in neural information processing systems 34 (2021), 6747--6761."},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583247"},{"key":"e_1_3_2_2_43_1","volume-title":"International conference on machine learning. PMLR, 1139--1147","author":"Sutskever Ilya","year":"2013","unstructured":"Ilya Sutskever, James Martens, George Dahl, and Geoffrey Hinton. 2013. On the importance of initialization and momentum in deep learning. In International conference on machine learning. PMLR, 1139--1147."},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2019.2893638"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220021"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3187556"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783273"},{"key":"e_1_3_2_2_48_1","volume-title":"Dualgnn: Dual graph neural network for multimedia recommendation","author":"Wang Qifan","year":"2021","unstructured":"Qifan Wang, Yinwei Wei, Jianhua Yin, Jianlong Wu, Xuemeng Song, and Liqiang Nie. 2021. Dualgnn: Dual graph neural network for multimedia recommendation. IEEE Transactions on Multimedia (2021)."},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413556"},{"key":"e_1_3_2_2_50_1","volume-title":"Proceedings of the 27th ACM international conference on multimedia. 1437--1445","author":"Nie Liqiang","year":"2019","unstructured":"YinweiWei, XiangWang, Liqiang Nie, Xiangnan He, Richang Hong, and Tat-Seng Chua. 2019. MMGCN: Multi-modal graph convolution network for personalized recommendation of micro-video. In Proceedings of the 27th ACM international conference on multimedia. 1437--1445."},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462914"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583277"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939673"},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-00126-0_15"},{"key":"e_1_3_2_2_55_1","volume-title":"International Conference on Machine Learning. PMLR, 26982--26992","author":"Zhao Yang","year":"2022","unstructured":"Yang Zhao, Hao Zhang, and Xiuyuan Hu. 2022. Penalizing gradient norm for efficiently improving generalization in deep learning. In International Conference on Machine Learning. PMLR, 26982--26992."},{"key":"e_1_3_2_2_56_1","volume-title":"Let's Think Outside the Box: Exploring Leap-of-Thought in Large Language Models with Creative Humor Generation. arXiv preprint arXiv:2312.02439","author":"Zhong Shanshan","year":"2023","unstructured":"Shanshan Zhong, Zhongzhan Huang, Shanghua Gao, Wushao Wen, Liang Lin, Marinka Zitnik, and Pan Zhou. 2023. Let's Think Outside the Box: Exploring Leap-of-Thought in Large Language Models with Creative Humor Generation. arXiv preprint arXiv:2312.02439 (2023)."},{"key":"e_1_3_2_2_57_1","volume-title":"ASR: Attention-alike Structural Re-parameterization. arXiv preprint arXiv:2304.06345","author":"Zhong Shanshan","year":"2023","unstructured":"Shanshan Zhong, Zhongzhan Huang, Wushao Wen, Jinghui Qin, and Liang Lin. 2023. ASR: Attention-alike Structural Re-parameterization. arXiv preprint arXiv:2304.06345 (2023)."},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611863"},{"key":"e_1_3_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.213"},{"key":"e_1_3_2_2_60_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, and Zhiqi Shen. 2023. Enhancing Dyadic Relations with Homogeneous Graphs for Multimodal Recommendation. arXiv preprint arXiv:2301.12097 (2023)."},{"key":"e_1_3_2_2_61_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. 2023. A Comprehensive Survey on Multimodal Recommender Systems: Taxonomy, Evaluation, and Future Directions. arXiv preprint arXiv:2302.04473 (2023)."},{"key":"e_1_3_2_2_62_1","volume-title":"A tale of two graphs: Freezing and denoising graph structures for multimodal recommendation. arXiv preprint arXiv:2211.06924","author":"Zhou Xin","year":"2022","unstructured":"Xin Zhou. 2022. A tale of two graphs: Freezing and denoising graph structures for multimodal recommendation. arXiv preprint arXiv:2211.06924 (2022)."},{"key":"e_1_3_2_2_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/SCC.2016.35"},{"key":"e_1_3_2_2_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE55515.2023.00100"},{"key":"e_1_3_2_2_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/3591469"},{"key":"e_1_3_2_2_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583251"},{"key":"e_1_3_2_2_67_1","volume-title":"Surrogate gap minimization improves sharpness-aware training. arXiv preprint arXiv:2203.08065","author":"Zhuang Juntang","year":"2022","unstructured":"Juntang Zhuang, Boqing Gong, Liangzhe Yuan, Yin Cui, Hartwig Adam, Nicha Dvornek, Sekhar Tatikonda, James Duncan, and Ting Liu. 2022. Surrogate gap minimization improves sharpness-aware training. arXiv preprint arXiv:2203.08065 (2022)."}],"event":{"name":"WWW '24: The ACM Web Conference 2024","location":"Singapore Singapore","acronym":"WWW '24","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM Web Conference 2024"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3589334.3645553","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3589334.3645553","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:25:17Z","timestamp":1755822317000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3589334.3645553"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":67,"alternative-id":["10.1145\/3589334.3645553","10.1145\/3589334"],"URL":"https:\/\/doi.org\/10.1145\/3589334.3645553","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]},"assertion":[{"value":"2024-05-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}