{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T05:04:12Z","timestamp":1765343052468,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":52,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755631","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:27:39Z","timestamp":1761377259000},"page":"2044-2053","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Disentangling Homophily and Heterophily in Multimodal Graph Clustering"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-2555-2753","authenticated-orcid":false,"given":"Zhaochen","family":"Guo","sequence":"first","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, Sichuan, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3878-0177","authenticated-orcid":false,"given":"Zhixiang","family":"Shen","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, Sichuan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3801-5876","authenticated-orcid":false,"given":"Xuanting","family":"Xie","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, Sichuan, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3493-6403","authenticated-orcid":false,"given":"Liangjian","family":"Wen","sequence":"additional","affiliation":[{"name":"Southwestern University of Finance and Economics, Chengdu, Sichuan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4103-0954","authenticated-orcid":false,"given":"Zhao","family":"Kang","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, Sichuan, China"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16515"},{"key":"e_1_3_2_2_2_1","volume-title":"The Twelfth International Conference on Learning Representations","author":"Chen Jingyu","year":"2023","unstructured":"Jingyu Chen, Runlin Lei, and Zhewei Wei. Polygcl: Graph contrastive learning via learnable spectral polynomial filters. In The Twelfth International Conference on Learning Representations, 2023."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531992"},{"key":"e_1_3_2_2_4_1","volume-title":"Adaptive universal generalized pagerank graph neural network. arXiv preprint arXiv:2006.07988","author":"Chien Eli","year":"2020","unstructured":"Eli Chien, Jianhao Peng, Pan Li, and Olgica Milenkovic. Adaptive universal generalized pagerank graph neural network. arXiv preprint arXiv:2006.07988, 2020."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00624-6"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380079"},{"key":"e_1_3_2_2_7_1","volume-title":"Layla El Asri, and Seyed Mehran Kazemi. Slaps: Self-supervision improves structure learning for graph neural networks","author":"Fatemi Bahare","year":"2021","unstructured":"Bahare Fatemi, Layla El Asri, and Seyed Mehran Kazemi. Slaps: Self-supervision improves structure learning for graph neural networks, 2021."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380297"},{"key":"e_1_3_2_2_9_1","volume-title":"International Conference on Learning Representations","author":"Gasteiger Johannes","year":"2018","unstructured":"Johannes Gasteiger, Aleksandar Bojchevski, and Stephan G\u00fcnnemann. Predict then propagate: Graph neural networks meet personalized pagerank. In International Conference on Learning Representations, 2018."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557339"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3434556"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714818"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714818"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-022-07862-6"},{"key":"e_1_3_2_2_16_1","volume-title":"International Conference on Learning Representations","author":"Jin Wengong","year":"2019","unstructured":"Wengong Jin, Kevin Yang, Regina Barzilay, and Tommi Jaakkola. Learning multimodal graph-to-graph translation for molecule optimization. In International Conference on Learning Representations, 2019."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449971"},{"key":"e_1_3_2_2_18_1","first-page":"1","article-title":"A simple framework for complex data clustering","author":"Kang Zhao","year":"2024","unstructured":"Zhao Kang, Xuanting Xie, Bingheng Li, and Erlin Pan. Cdc: A simple framework for complex data clustering. IEEE Transactions on Neural Networks and Learning Systems, pages 1-12, 2024.","journal-title":"IEEE Transactions on Neural Networks and Learning Systems, pages"},{"key":"e_1_3_2_2_19_1","volume-title":"Kipf and Max Welling. Variational graph auto-encoders","author":"Thomas","year":"2016","unstructured":"Thomas N. Kipf and Max Welling. Variational graph auto-encoders, 2016."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12859-023-05622-4"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583554"},{"issue":"02","key":"e_1_3_2_2_22_1","first-page":"1872","article-title":"Multi-view attributed graph clustering","volume":"35","author":"Lin Zhiping","year":"2023","unstructured":"Zhiping Lin, Zhao Kang, Lizong Zhang, and Ling Tian. Multi-view attributed graph clustering. IEEE Transactions on Knowledge & Data Engineering, 35(02):1872-1880, 2023.","journal-title":"IEEE Transactions on Knowledge & Data Engineering"},{"issue":"1","key":"e_1_3_2_2_23_1","first-page":"857","article-title":"Generative or contrastive","volume":"35","author":"Liu Xiao","year":"2021","unstructured":"Xiao Liu, Fanjin Zhang, Zhenyu Hou, Li Mian, Zhaoyu Wang, Jing Zhang, and Jie Tang. Self-supervised learning: Generative or contrastive. IEEE Transactions on Knowledge and Data Engineering, 35(1):857-876, 2021.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014456"},{"key":"e_1_3_2_2_25_1","volume-title":"CoRR","author":"Luan Sitao","year":"2024","unstructured":"Sitao Luan, Chenqing Hua, Qincheng Lu, Liheng Ma, Lirong Wu, Xinyu Wang, Minkai Xu, Xiao-Wen Chang, Doina Precup, Rex Ying, et al. The heterophilic graph learning handbook: Benchmarks, models, theoretical analysis, applications and challenges. CoRR, 2024."},{"key":"e_1_3_2_2_26_1","volume-title":"Revisiting heterophily for graph neural networks. Advances in neural information processing systems, 35:1362-1375","author":"Luan Sitao","year":"2022","unstructured":"Sitao Luan, Chenqing Hua, Qincheng Lu, Jiaqi Zhu, Mingde Zhao, Shuyuan Zhang, Xiao-Wen Chang, and Doina Precup. Revisiting heterophily for graph neural networks. Advances in neural information processing systems, 35:1362-1375, 2022."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3268069"},{"key":"e_1_3_2_2_28_1","first-page":"24983","volume-title":"International Conference on Machine Learning","author":"Mo Yujie","year":"2023","unstructured":"Yujie Mo, Yajie Lei, Jialie Shen, Xiaoshuang Shi, Heng Tao Shen, and Xiaofeng Zhu. Disentangled multiplex graph representation learning. In International Conference on Machine Learning, pages 24983-25005. PMLR, 2023."},{"key":"e_1_3_2_2_29_1","volume-title":"Multi-view contrastive graph clustering. Advances in neural information processing systems, 34:2148-2159","author":"Pan Erlin","year":"2021","unstructured":"Erlin Pan and Zhao Kang. Multi-view contrastive graph clustering. Advances in neural information processing systems, 34:2148-2159, 2021."},{"key":"e_1_3_2_2_30_1","first-page":"26868","volume-title":"International conference on machine learning","author":"Pan Erlin","year":"2023","unstructured":"Erlin Pan and Zhao Kang. Beyond homophily: Reconstructing structure for graph-agnostic clustering. In International conference on machine learning, pages 26868-26877. PMLR, 2023."},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5985"},{"key":"e_1_3_2_2_32_1","volume-title":"Learning on multimodal graphs: A survey. arXiv preprint arXiv:2402.05322","author":"Peng Ciyuan","year":"2024","unstructured":"Ciyuan Peng, Jiayuan He, and Feng Xia. Learning on multimodal graphs: A survey. arXiv preprint arXiv:2402.05322, 2024."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i13.29383"},{"key":"e_1_3_2_2_34_1","first-page":"8748","volume-title":"International conference on machine learning","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. Learning transferable visual models from natural language supervision. In International conference on machine learning, pages 8748-8763. PmLR, 2021."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681325"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2025.3540063"},{"key":"e_1_3_2_2_37_1","first-page":"31629","volume-title":"Advances in Neural Information Processing Systems","volume":"37","author":"Shen Zhixiang","year":"2024","unstructured":"Zhixiang Shen, Shuo Wang, and Zhao Kang. Beyond redundancy: Information-aware unsupervised multiplex graph structure learning. In Advances in Neural Information Processing Systems, volume 37, pages 31629-31658, 2024."},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2020.102277"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1176348768"},{"key":"e_1_3_2_2_40_1","volume-title":"Deep graph infomax","author":"Velickovic Petar","year":"2018","unstructured":"Petar Velickovic, William Fedus, William L. Hamilton, Pietro Li\u00f2, Yoshua Bengio, and R Devon Hjelm. Deep graph infomax, 2018."},{"key":"e_1_3_2_2_41_1","volume-title":"An information criterion for controlled disentanglement of multimodal data","author":"Wang Chenyu","year":"2025","unstructured":"Chenyu Wang, Sharut Gupta, Xinyi Zhang, Sana Tonekaboni, Stefanie Jegelka, Tommi Jaakkola, and Caroline Uhler. An information criterion for controlled disentanglement of multimodal data, 2025."},{"volume-title":"Forty-second International Conference on Machine Learning.","author":"Wang Shuo","key":"e_1_3_2_2_42_1","unstructured":"Shuo Wang, Shunyang Huang, Jinghui Yuan, Zhixiang Shen, et al. Cooperation of experts: Fusing heterogeneous information with large margin. In Forty-second International Conference on Machine Learning."},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612266"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3240863"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i20.35473"},{"key":"e_1_3_2_2_48_1","volume-title":"When graph meets multimodal: Benchmarking on multimodal attributed graphs learning. arXiv preprint arXiv:2410.09132","author":"Yan Hao","year":"2024","unstructured":"Hao Yan, Chaozhuo Li, Zhigang Yu, Jun Yin, Ruochen Liu, Peiyan Zhang, Weihao Han, Mingzheng Li, Zhengxin Zeng, Hao Sun, et al. When graph meets multimodal: Benchmarking on multimodal attributed graphs learning. arXiv preprint arXiv:2410.09132, 2024."},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01902"},{"key":"e_1_3_2_2_50_1","volume-title":"NeurIPS 2023 Workshop: New Frontiers in Graph Learning","author":"Yoon Minji","year":"2023","unstructured":"Minji Yoon, Jing Yu Koh, Bryan Hooi, and Russ Salakhutdinov. Multimodal graph learning for generative tasks. In NeurIPS 2023 Workshop: New Frontiers in Graph Learning, 2023."},{"key":"e_1_3_2_2_51_1","volume-title":"Graph transformer networks. Advances in neural information processing systems, 32","author":"Yun Seongjun","year":"2019","unstructured":"Seongjun Yun, Minbyul Jeong, Raehyun Kim, Jaewoo Kang, and Hyunwoo J Kim. Graph transformer networks. Advances in neural information processing systems, 32, 2019."},{"key":"e_1_3_2_2_52_1","volume-title":"CoRR","author":"Zhu Jing","year":"2024","unstructured":"Jing Zhu, Yuhang Zhou, Shengyi Qian, Zhongmou He, Tong Zhao, Neil Shah, and Danai Koutra. Multimodal graph benchmark. CoRR, 2024."}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755631","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:59:48Z","timestamp":1765342788000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755631"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":52,"alternative-id":["10.1145\/3746027.3755631","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755631","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}