{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T17:15:38Z","timestamp":1775841338982,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":58,"publisher":"ACM","funder":[{"name":"National Natural Science Foundation of China","award":["62302131"],"award-info":[{"award-number":["62302131"]}]},{"name":"China Postdoctoral Science Foundation","award":["GZB20250405"],"award-info":[{"award-number":["GZB20250405"]}]},{"name":"China Postdoctoral Science Foundation","award":["GZC20251050"],"award-info":[{"award-number":["GZC20251050"]}]},{"name":"China Postdoctoral Science Foundation","award":["2025M781526"],"award-info":[{"award-number":["2025M781526"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3774904.3792719","type":"proceedings-article","created":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T21:54:39Z","timestamp":1775771679000},"page":"4429-4439","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Towards Foundation Models for MMKG: Multi-Task Inductive Generalization via Task-Aware Routing"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-4454-9889","authenticated-orcid":false,"given":"Shundong","family":"Yang","sequence":"first","affiliation":[{"name":"Zhengzhou University, Zhengzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4682-4839","authenticated-orcid":false,"given":"Jing","family":"Yang","sequence":"additional","affiliation":[{"name":"Zhengzhou University, Zhengzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9773-1265","authenticated-orcid":false,"given":"Xiaowen","family":"Jiang","sequence":"additional","affiliation":[{"name":"Zhengzhou University, Zhengzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5146-4667","authenticated-orcid":false,"given":"Xiaofen","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhengzhou University, Zhengzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7986-4244","authenticated-orcid":false,"given":"Laurence T.","family":"Yang","sequence":"additional","affiliation":[{"name":"Zhengzhou University, Zhengzhou, China and Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4096-9134","authenticated-orcid":false,"given":"Yuan","family":"Gao","sequence":"additional","affiliation":[{"name":"Zhengzhou University, Zhengzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3276-7707","authenticated-orcid":false,"given":"Xinfa","family":"Jiang","sequence":"additional","affiliation":[{"name":"Hainan University, Hainan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2051-7600","authenticated-orcid":false,"given":"Jie","family":"Chen","sequence":"additional","affiliation":[{"name":"Zhengzhou University, Zhengzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8195-9322","authenticated-orcid":false,"given":"Chaojun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Hainan University, Hainan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,4,12]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Translating embeddings for modeling multi-relational data. Advances in neural information processing systems","author":"Bordes Antoine","year":"2013","unstructured":"Antoine Bordes, Nicolas Usunier, Alberto Garcia-Duran, Jason Weston, and Oksana Yakhnenko. 2013a. Translating embeddings for modeling multi-relational data. Advances in neural information processing systems, Vol. 26 (2013)."},{"key":"e_1_3_2_1_2_1","volume-title":"Translating embeddings for modeling multi-relational data. Advances in neural information processing systems","author":"Bordes Antoine","year":"2013","unstructured":"Antoine Bordes, Nicolas Usunier, Alberto Garcia-Duran, Jason Weston, and Oksana Yakhnenko. 2013b. Translating embeddings for modeling multi-relational data. Advances in neural information processing systems, Vol. 26 (2013)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i8.16850"},{"key":"e_1_3_2_1_4_1","volume-title":"Otkge: Multi-modal knowledge graph embeddings via optimal transport. Advances in Neural Information Processing Systems","author":"Cao Zongsheng","year":"2022","unstructured":"Zongsheng Cao, Qianqian Xu, Zhiyong Yang, Yuan He, Xiaochun Cao, and Qingming Huang. 2022. Otkge: Multi-modal knowledge graph embeddings via optimal transport. Advances in Neural Information Processing Systems (2022)."},{"key":"e_1_3_2_1_5_1","volume-title":"Multitask learning. Machine learning","author":"Caruana Rich","year":"1997","unstructured":"Rich Caruana. 1997. Multitask learning. Machine learning, Vol. 28, 1 (1997), 41-75."},{"key":"e_1_3_2_1_6_1","first-page":"904","article-title":"Hybrid transformer with multi-level fusion for multimodal knowledge graph completion","author":"Chen Xiang","year":"2022","unstructured":"Xiang Chen, Ningyu Zhang, Lei Li, Shumin Deng, Chuanqi Tan, Changliang Xu, Fei Huang, Luo Si, and Huajun Chen. 2022. Hybrid transformer with multi-level fusion for multimodal knowledge graph completion. In ACM SIGIR. 904-915.","journal-title":"ACM SIGIR."},{"key":"e_1_3_2_1_7_1","first-page":"3317","article-title":"MEAformer","author":"Chen Zhuo","year":"2023","unstructured":"Zhuo Chen, Jiaoyan Chen, Wen Zhang, Lingbing Guo, Yin Fang, Yufeng Huang, Yichi Zhang, Yuxia Geng, Jeff Z. Pan, Wenting Song, and Huajun Chen. 2023. MEAformer: Multi-modal Entity Alignment Transformer for Meta Modality Hybrid. In ACM Multimedia. 3317-3327.","journal-title":"Multi-modal Entity Alignment Transformer for Meta Modality Hybrid. In ACM Multimedia."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671511"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01763"},{"key":"e_1_3_2_1_10_1","volume-title":"Towards Foundation Models for Knowledge Graph Reasoning. In The Twelfth International Conference on Learning Representations.","author":"Galkin Mikhail","year":"2024","unstructured":"Mikhail Galkin, Xinyu Yuan, Hesham Mostafa, Jian Tang, and Zhaocheng Zhu. 2024. Towards Foundation Models for Knowledge Graph Reasoning. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_1_11_1","first-page":"993","article-title":"Multimodal entity linking: a new dataset and a baseline","author":"Gan Jingru","year":"2021","unstructured":"Jingru Gan, Jinchang Luo, Haiwei Wang, Shuhui Wang, Wei He, and Qingming Huang. 2021. Multimodal entity linking: a new dataset and a baseline. In ACM Multimedia. 993-1001.","journal-title":"ACM Multimedia."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i11.33278"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3690624.3709306"},{"key":"e_1_3_2_1_14_1","volume-title":"Proceedings of the 40th International Conference on Machine Learning. 18796-18809","author":"Jaejun Lee Chanyoung Chung","year":"2023","unstructured":"Chanyoung Chung Jaejun Lee and Joyce Jiyoung Whang. 2023. InGram: Inductive knowledge graph embedding via relation graphs. In Proceedings of the 40th International Conference on Machine Learning. 18796-18809."},{"key":"e_1_3_2_1_15_1","volume-title":"Rajiv Ratn Shah, and Raghava Mutharaju","author":"Kharbanda Mayank","year":"2025","unstructured":"Mayank Kharbanda, Rajiv Ratn Shah, and Raghava Mutharaju. 2025. RConE: Rough Cone Embedding for Multi-Hop Logical Query Answering on Multi-Modal Knowledge Graphs. IEEE Transactions on Knowledge and Data Engineering (2025)."},{"key":"e_1_3_2_1_16_1","volume-title":"International conference on machine learning. PMLR, 5583-5594","author":"Kim Wonjae","year":"2021","unstructured":"Wonjae Kim, Bokyung Son, and Ildoo Kim. 2021. Vilt: Vision-and-language transformer without convolution or region supervision. In International conference on machine learning. PMLR, 5583-5594."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3729906"},{"key":"e_1_3_2_1_18_1","volume-title":"VISTA: Visual-Textual Knowledge Graph Representation Learning. In EMNLP.","author":"Lee Jaejun","year":"2023","unstructured":"Jaejun Lee, Chanyoung Chung, Hochang Lee, Sungho Jo, and Joyce Whang. 2023. VISTA: Visual-Textual Knowledge Graph Representation Learning. In EMNLP."},{"key":"e_1_3_2_1_19_1","volume-title":"Align before fuse: Vision and language representation learning with momentum distillation. Advances in neural information processing systems","author":"Li Junnan","year":"2021","unstructured":"Junnan Li, Ramprasaath Selvaraju, Akhilesh Gotmare, Shafiq Joty, Caiming Xiong, and Steven Chu Hong Hoi. 2021. Align before fuse: Vision and language representation learning with momentum distillation. Advances in neural information processing systems, Vol. 34 (2021), 9694-9705."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671769"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583554"},{"key":"e_1_3_2_1_22_1","volume-title":"Proceedings of the International Conference on Computational Linguistics. 2572-2584","author":"Lin Zhenxi","year":"2022","unstructured":"Zhenxi Lin, Ziheng Zhang, Meng Wang, Yinghui Shi, Xian Wu, and Yefeng Zheng. 2022. Multi-modal Contrastive Representation Learning for Entity Alignment. In Proceedings of the International Conference on Computational Linguistics. 2572-2584."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16550"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3679793"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714860"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Ye Liu Hui Li Alberto Garcia-Duran Mathias Niepert Daniel Onoro-Rubio and David S Rosenblum. 2019. MMKG: multi-modal knowledge graphs. In ESWC.","DOI":"10.1007\/978-3-030-21348-0_30"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.450"},{"key":"e_1_3_2_1_28_1","first-page":"225","article-title":"A multimodal translation-based approach for knowledge graph representation learning","author":"Mousselly-Sergieh Hatem","year":"2018","unstructured":"Hatem Mousselly-Sergieh, Teresa Botschen, Iryna Gurevych, and Stefan Roth. 2018. A multimodal translation-based approach for knowledge graph representation learning. In SEMEAVL. 225-234.","journal-title":"SEMEAVL."},{"key":"e_1_3_2_1_29_1","volume-title":"International conference on machine learning. 8748-8763","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., 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. 8748-8763."},{"key":"e_1_3_2_1_30_1","unstructured":"Senbao Shi Zhenran Xu Baotian Hu and Min Zhang. 2024. Generative Multimodal Entity Linking. In LREC\/COLING."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.3390\/s22103799"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714926"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29867"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680954"},{"key":"e_1_3_2_1_35_1","volume-title":"International Conference on Learning Representations.","author":"Sun Zhiqing","year":"2019","unstructured":"Zhiqing Sun, Zhi-Hong Deng, Jian-Yun Nie, and Jian Tang. 2019. RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_36_1","first-page":"628","article-title":"Cross-Lingual Entity Alignment via Joint Attribute-Preserving Embedding","author":"Sun Zequn","year":"2017","unstructured":"Zequn Sun, Wei Hu, and Chengkai Li. 2017. Cross-Lingual Entity Alignment via Joint Attribute-Preserving Embedding. In ISWC. 628-644.","journal-title":"ISWC."},{"key":"e_1_3_2_1_37_1","volume-title":"International Conference on Machine Learning (ICML)","volume":"48","author":"Trouillon Th\u00e9o","year":"2016","unstructured":"Th\u00e9o Trouillon, Johannes Welbl, Sebastian Riedel, \u00c9ric Gaussier, and Guillaume Bouchard. 2016. Complex embeddings for simple link prediction. In International Conference on Machine Learning (ICML), Vol. 48. 2071-2080."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/2629489"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i28.35230"},{"key":"e_1_3_2_1_40_1","first-page":"2391","article-title":"TIVA-KG: A multimodal knowledge graph with text, image, video and audio","author":"Wang Xin","year":"2023","unstructured":"Xin Wang, Benyuan Meng, Hong Chen, Yuan Meng, Ke Lv, and Wenwu Zhu. 2023. TIVA-KG: A multimodal knowledge graph with text, image, video and audio. In ACM MM. 2391-2399.","journal-title":"ACM MM."},{"key":"e_1_3_2_1_41_1","unstructured":"Zehong Wang Zheyuan Liu Tianyi Ma Jiazheng Li Zheyuan Zhang Xingbo Fu Yiyang Li Zhengqing Yuan Wei Song Yijun Ma et al. 2025. Graph Foundation Models: A Comprehensive Survey. arXiv preprint arXiv:2505.15116 (2025)."},{"key":"e_1_3_2_1_42_1","volume-title":"Anygraph: Graph foundation model in the wild. arXiv preprint arXiv:2408.10700","author":"Xia Lianghao","year":"2024","unstructured":"Lianghao Xia and Chao Huang. 2024. Anygraph: Graph foundation model in the wild. arXiv preprint arXiv:2408.10700 (2024)."},{"key":"e_1_3_2_1_43_1","unstructured":"Ruobing Xie Zhiyuan Liu Huanbo Luan and Maosong Sun. 2017. Image-embodied Knowledge Representation Learning. In IJCAI."},{"key":"e_1_3_2_1_44_1","first-page":"3857","article-title":"Relation-enhanced negative sampling for multimodal knowledge graph completion","author":"Xu Derong","year":"2022","unstructured":"Derong Xu, Tong Xu, Shiwei Wu, Jingbo Zhou, and Enhong Chen. 2022. Relation-enhanced negative sampling for multimodal knowledge graph completion. In ACM MM. 3857-3866.","journal-title":"ACM MM."},{"key":"e_1_3_2_1_45_1","volume-title":"JieMing Yang, et al.","author":"Yang Jing","year":"2024","unstructured":"Jing Yang, Xiaowen Jiang, Yuan Gao, Laurence Tianruo Yang, JieMing Yang, et al., 2024a. Generalize to Fully Unseen Graphs: Learn Transferable Hyper-Relation Structures for Inductive Link Prediction. In ACM Multimedia 2024."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681696"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714781"},{"key":"e_1_3_2_1_48_1","volume-title":"Proceedings of the 33rd International Conference on Neural Information Processing Systems. 2735-2745","author":"Zhang Shuai","year":"2019","unstructured":"Shuai Zhang, Yi Tay, Lina Yao, and Qi Liu. 2019. Quaternion knowledge graph embeddings. In Proceedings of the 33rd International Conference on Neural Information Processing Systems. 2735-2745."},{"key":"e_1_3_2_1_49_1","volume-title":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases.","author":"Zhang Xuan","year":"2022","unstructured":"Xuan Zhang, Xun Liang, Xiangping Zheng, Bo Wu, and Yuhui Guo. 2022. MULTIFORM: few-shot knowledge graph completion via multi-modal contexts. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases."},{"key":"e_1_3_2_1_50_1","first-page":"91","article-title":"NativE","author":"Zhang Yichi","year":"2024","unstructured":"Yichi Zhang, Zhuo Chen, Lingbing Guo, Yajing Xu, Binbin Hu, Ziqi Liu, Wen Zhang, and Huajun Chen. 2024a. NativE: Multi-modal Knowledge Graph Completion in the Wild. In SIGIR. ACM, 91-101.","journal-title":"Multi-modal Knowledge Graph Completion in the Wild. In SIGIR. ACM"},{"key":"e_1_3_2_1_51_1","unstructured":"Yichi Zhang Zhuo Chen Lingbing Guo Yajing Xu Binbin Hu Ziqi Liu Wen Zhang and Huajun Chen. 2025a. Multiple Heads are Better than One: Mixture of Modality Knowledge Experts for Entity Representation Learning. In ICLR."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i12.33454"},{"key":"e_1_3_2_1_53_1","volume-title":"Unleashing the Power of Imbalanced Modality Information for Multi-modal Knowledge Graph Completion. LREC-COLING","author":"Zhang Yichi","year":"2024","unstructured":"Yichi Zhang, Zhuo Chen, Lei Liang, Huajun Chen, and Wen Zhang. 2024b. Unleashing the Power of Imbalanced Modality Information for Multi-modal Knowledge Graph Completion. LREC-COLING (2024)."},{"key":"e_1_3_2_1_54_1","volume-title":"Knowledge graph completion with pre-trained multimodal transformer and twins negative sampling. CoRR","author":"Zhang Yichi","year":"2022","unstructured":"Yichi Zhang and Wen Zhang. 2022. Knowledge graph completion with pre-trained multimodal transformer and twins negative sampling. CoRR (2022)."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.243"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.719"},{"key":"e_1_3_2_1_57_1","volume-title":"Wei Chen, and Lei Zhao.","author":"Zheng Shangfei","year":"2025","unstructured":"Shangfei Zheng, Hongzhi Yin, Tong Chen, Quoc Viet Hung Nguyen, Wei Chen, and Lei Zhao. 2025. Do as I can, not as I get: Topology-aware multi-hop reasoning on multi-modal knowledge graphs. IEEE Transactions on Knowledge and Data Engineering (2025)."},{"key":"e_1_3_2_1_58_1","volume-title":"Proceedings of the 35th Conference on Neural Information Processing System. 29476-29490","author":"Zhu Zhaocheng","year":"2021","unstructured":"Zhaocheng Zhu, Zuobai Zhang, Louis-Pascal Xhonneux, and Jian Tang. 2021. Neural bellman-ford networks: A general graph neural network framework for link prediction. In Proceedings of the 35th Conference on Neural Information Processing System. 29476-29490."}],"event":{"name":"WWW '26: The ACM Web Conference 2026","location":"Dubai United Arab Emirates","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM Web Conference 2026"],"original-title":[],"deposited":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T16:34:13Z","timestamp":1775838853000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774904.3792719"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,12]]},"references-count":58,"alternative-id":["10.1145\/3774904.3792719","10.1145\/3774904"],"URL":"https:\/\/doi.org\/10.1145\/3774904.3792719","relation":{},"subject":[],"published":{"date-parts":[[2026,4,12]]},"assertion":[{"value":"2026-04-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}