{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T03:47:21Z","timestamp":1790912841460,"version":"4.1.0"},"publisher-location":"New York, NY, USA","reference-count":47,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,8]],"date-time":"2024-10-08T00:00:00Z","timestamp":1728345600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,8]]},"DOI":"10.1145\/3640457.3688096","type":"proceedings-article","created":{"date-parts":[[2024,10,8]],"date-time":"2024-10-08T15:39:28Z","timestamp":1728401968000},"page":"518-527","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":18,"title":["A Unified Graph Transformer for Overcoming Isolations in Multi-modal Recommendation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7752-8650","authenticated-orcid":false,"given":"Zixuan","family":"Yi","sequence":"first","affiliation":[{"name":"School of Computing Science, University of Glasgow, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4701-3223","authenticated-orcid":false,"given":"Iadh","family":"Ounis","sequence":"additional","affiliation":[{"name":"School of Computing Science, University of Glasgow, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,8]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Proc. of NeurIPS.","author":"Bao Hangbo","year":"2022","unstructured":"Hangbo Bao, Wenhui Wang, Li Dong, Qiang Liu, Owais\u00a0Khan Mohammed, Kriti Aggarwal, Subhojit Som, Songhao Piao, and Furu Wei. 2022. Vlmo: Unified vision-language pre-training with mixture-of-modality-experts. In Proc. of NeurIPS."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557262"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657747"},{"key":"e_1_3_2_1_4_1","volume-title":"Recommender systems leveraging multimedia content. Computing Surveys","author":"Deldjoo Yashar","year":"2020","unstructured":"Yashar Deldjoo, Markus Schedl, Paolo Cremonesi, and Gabriella Pasi. 2020. Recommender systems leveraging multimedia content. Computing Surveys (2020)."},{"key":"e_1_3_2_1_5_1","volume-title":"Proc. of ICML.","author":"Donahue Jeff","year":"2014","unstructured":"Jeff Donahue, Yangqing Jia, Oriol Vinyals, Judy Hoffman, Ning Zhang, Eric Tzeng, and Trevor Darrell. 2014. Decaf: A deep convolutional activation feature for generic visual recognition. In Proc. of ICML."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475634"},{"key":"e_1_3_2_1_7_1","volume-title":"3SHNet: Boosting image\u2013sentence retrieval via visual semantic\u2013spatial self-highlighting. Information Processing & Management","author":"Ge Xuri","year":"2024","unstructured":"Xuri Ge, Songpei Xu, Fuhai Chen, Jie Wang, Guoxin Wang, Shan An, and Joemon\u00a0M Jose. 2024. 3SHNet: Boosting image\u2013sentence retrieval via visual semantic\u2013spatial self-highlighting. Information Processing & Management (2024)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.9973"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401063"},{"key":"e_1_3_2_1_12_1","volume-title":"Proc. of ACL.","author":"He Xuehai","year":"2023","unstructured":"Xuehai He and Xin\u00a0Eric Wang. 2023. Multi-modal graph transformer for multimodal question answering. In Proc. of ACL."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2018.00035"},{"key":"e_1_3_2_1_14_1","volume-title":"Proc. of ICLR.","author":"Kingma P","year":"2014","unstructured":"Diederik\u00a0P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. In Proc. of ICLR."},{"key":"e_1_3_2_1_15_1","volume-title":"Proc. of ICLR.","author":"Kolesnikov Alexander","year":"2022","unstructured":"Alexander Kolesnikov, Alexey Dosovitskiy, Dirk Weissenborn, Georg Heigold, Jakob Uszkoreit, Lucas Beyer, Matthias Minderer, Mostafa Dehghani, Neil Houlsby, Sylvain Gelly, Thomas Unterthiner, and Xiaohua Zhai. 2022. An image is worth 16x16 words: Transformers for image recognition at scale. In Proc. of ICLR."},{"key":"e_1_3_2_1_16_1","volume-title":"Proc. of ICML.","author":"Le Quoc","year":"2014","unstructured":"Quoc Le and Tomas Mikolov. 2014. Distributed representations of sentences and documents. In Proc. of ICML."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591723"},{"key":"e_1_3_2_1_18_1","volume-title":"Proc. of ICML.","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022. BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In Proc. of ICML."},{"key":"e_1_3_2_1_19_1","volume-title":"Edge-enhanced global disentangled graph neural network for sequential recommendation. Transactions on Knowledge Discovery from Data","author":"Li Yunyi","year":"2023","unstructured":"Yunyi Li, Yongjing Hao, Pengpeng Zhao, Guanfeng Liu, Yanchi Liu, Victor\u00a0S Sheng, and Xiaofang Zhou. 2023. Edge-enhanced global disentangled graph neural network for sequential recommendation. Transactions on Knowledge Discovery from Data (2023)."},{"key":"e_1_3_2_1_20_1","volume-title":"Multi-modal recommender systems: A Survey. arXiv preprint arXiv:2302.03883","author":"Liu Qidong","year":"2023","unstructured":"Qidong Liu, Jiaxi Hu, Yutian Xiao, Jingtong Gao, and Xiangyu Zhao. 2023. Multi-modal recommender systems: A Survey. arXiv preprint arXiv:2302.03883 (2023)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475709"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3523227.3546768"},{"key":"e_1_3_2_1_23_1","volume-title":"Language models are unsupervised multitask learners. OpenAI Blog","author":"Radford Alec","year":"2019","unstructured":"Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, Ilya Sutskever, 2019. Language models are unsupervised multitask learners. OpenAI Blog (2019)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"e_1_3_2_1_25_1","volume-title":"Proc. of UAI.","author":"Rendle Steffen","year":"2009","unstructured":"Steffen Rendle, Christoph Freudenthaler, Zeno Gantner, and Lars Schmidt-Thieme. 2009. BPR: Bayesian personalised ranking from implicit feedback. In Proc. of UAI."},{"key":"e_1_3_2_1_26_1","volume-title":"Proc. of UAI.","author":"Rendle Steffen","year":"2009","unstructured":"Steffen Rendle, Christoph Freudenthaler, Zeno Gantner, and Lars Schmidt-Thieme. 2009. BPR: Bayesian personalized ranking from implicit feedback. In Proc. of UAI."},{"key":"e_1_3_2_1_27_1","volume-title":"Proc. of ICML.","author":"Simonyan Karen","year":"2015","unstructured":"Karen Simonyan. 2015. Very deep convolutional networks for large-scale image recognition. In Proc. of ICML."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357895"},{"key":"e_1_3_2_1_29_1","volume-title":"Self-supervised learning for multimedia recommendation. Transactions on Multimedia","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 (2022)."},{"key":"e_1_3_2_1_30_1","volume-title":"Visualizing data using t-SNE.Journal of machine learning research","author":"Maaten Laurens Van\u00a0der","year":"2008","unstructured":"Laurens Van\u00a0der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE.Journal of machine learning research (2008)."},{"key":"e_1_3_2_1_31_1","volume-title":"Proc. of NeurIPS.","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan\u00a0N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Proc. of NeurIPS."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01838"},{"key":"e_1_3_2_1_33_1","volume-title":"Large-scale multi-modal pre-trained models: A comprehensive survey. Machine Intelligence Research","author":"Wang Xiao","year":"2023","unstructured":"Xiao Wang, Guangyao Chen, Guangwu Qian, Pengcheng Gao, Xiao-Yong Wei, Yaowei Wang, Yonghong Tian, and Wen Gao. 2023. Large-scale multi-modal pre-trained models: A comprehensive survey. Machine Intelligence Research (2023)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591716"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351034"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543829.3543837"},{"key":"e_1_3_2_1_37_1","volume-title":"Large multi-modal encoders for recommendation. arXiv preprint arXiv:2310.20343","author":"Yi Zixuan","year":"2023","unstructured":"Zixuan Yi, Zijun Long, Iadh Ounis, Craig Macdonald, and Richard Mccreadie. 2023. Large multi-modal encoders for recommendation. arXiv preprint arXiv:2310.20343 (2023)."},{"key":"e_1_3_2_1_38_1","volume-title":"Contrastive graph prompt-tuning for cross-domain recommendation. Transactions on Information Systems","author":"Yi Zixuan","year":"2023","unstructured":"Zixuan Yi, Iadh Ounis, and Craig Macdonald. 2023. Contrastive graph prompt-tuning for cross-domain recommendation. Transactions on Information Systems (2023)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-28238-6_19"},{"key":"e_1_3_2_1_40_1","volume-title":"A directional diffusion graph transformer for recommendation. arXiv preprint arXiv:2404.03326","author":"Yi Zixuan","year":"2024","unstructured":"Zixuan Yi, Xi Wang, and Iadh Ounis. 2024. A directional diffusion graph transformer for recommendation. arXiv preprint arXiv:2404.03326 (2024)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3532027"},{"key":"e_1_3_2_1_42_1","volume-title":"Proc. of NeuIPS.","author":"Ying Chengxuan","year":"2021","unstructured":"Chengxuan Ying, Tianle Cai, Shengjie Luo, Shuxin Zheng, Guolin Ke, Di He, Yanming Shen, and Tie-Yan Liu. 2021. Do transformers really perform badly for graph representation. In Proc. of NeuIPS."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475259"},{"key":"e_1_3_2_1_44_1","volume-title":"A comprehensive survey on multi-modal 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 multi-modal recommender systems: Taxonomy, evaluation, and future directions. arXiv preprint arXiv:2302.04473 (2023)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611943"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583251"},{"key":"e_1_3_2_1_47_1","volume-title":"Graph transformer collaborative filtering method for multi-behavior recommendations. Mathematics","author":"Zhu Wenhao","year":"2022","unstructured":"Wenhao Zhu, Yujun Xie, Qun Huang, Zehua Zheng, Xiaozhao Fang, Yonghui Huang, and Weijun Sun. 2022. Graph transformer collaborative filtering method for multi-behavior recommendations. Mathematics (2022)."}],"event":{"name":"RecSys '24: 18th ACM Conference on Recommender Systems","location":"Bari Italy","acronym":"RecSys '24","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGAI ACM Special Interest Group on Artificial Intelligence","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGIR ACM Special Interest Group on Information Retrieval","SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["18th ACM Conference on Recommender Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3640457.3688096","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3640457.3688096","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:58:29Z","timestamp":1750294709000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3640457.3688096"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,8]]},"references-count":47,"alternative-id":["10.1145\/3640457.3688096","10.1145\/3640457"],"URL":"https:\/\/doi.org\/10.1145\/3640457.3688096","relation":{},"subject":[],"published":{"date-parts":[[2024,10,8]]},"assertion":[{"value":"2024-10-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}