{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T13:09:57Z","timestamp":1765544997972,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,3,10]],"date-time":"2025-03-10T00:00:00Z","timestamp":1741564800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Natural Science Foundation of China","award":["62172443"],"award-info":[{"award-number":["62172443"]}]},{"name":"Hunan Provincial Natural Science Foundation of China","award":["2022JJ30053"],"award-info":[{"award-number":["2022JJ30053"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,3,10]]},"DOI":"10.1145\/3701551.3703571","type":"proceedings-article","created":{"date-parts":[[2025,2,26]],"date-time":"2025-02-26T12:33:36Z","timestamp":1740573216000},"page":"242-250","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["MoKGNN: Boosting Graph Neural Networks via Mixture of Generic and Task-Specific Language Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-7631-9375","authenticated-orcid":false,"given":"Hao","family":"Yan","sequence":"first","affiliation":[{"name":"Central South University, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8179-7503","authenticated-orcid":false,"given":"Chaozhuo","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6714-3476","authenticated-orcid":false,"given":"Jun","family":"Yin","sequence":"additional","affiliation":[{"name":"Central South University, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5533-6455","authenticated-orcid":false,"given":"Weihao","family":"Han","sequence":"additional","affiliation":[{"name":"Microsoft AI, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5027-7478","authenticated-orcid":false,"given":"Hao","family":"Sun","sequence":"additional","affiliation":[{"name":"Microsoft AI, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3615-4859","authenticated-orcid":false,"given":"Senzhang","family":"Wang","sequence":"additional","affiliation":[{"name":"Central South University, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5418-0455","authenticated-orcid":false,"given":"Jian","family":"Zhang","sequence":"additional","affiliation":[{"name":"Central South University, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1516-0480","authenticated-orcid":false,"given":"Jianxin","family":"Wang","sequence":"additional","affiliation":[{"name":"Central South University, Changsha, China"}]}],"member":"320","published-online":{"date-parts":[[2025,3,10]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3495883"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2015.2506556"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Zhikai Chen Haitao Mao Hang Li Wei Jin Hongzhi Wen Xiaochi Wei Shuaiqiang Wang Dawei Yin Wenqi Fan Hui Liu et al. 2024. Exploring the potential of large language models (llms) in learning on graphs. ACM SIGKDD Explorations Newsletter (2024).","DOI":"10.1145\/3655103.3655110"},{"key":"e_1_3_2_1_4_1","volume-title":"Proceedings of The Tenth International Conference on Learning Representations.","author":"Chien Eli","year":"2022","unstructured":"Eli Chien, Wei-Cheng Chang, Cho-Jui Hsieh, Hsiang-Fu Yu, Jiong Zhang, Olgica Milenkovic, and Inderjit S Dhillon. 2022. Node feature extraction by selfsupervised multi-scale neighborhood prediction. In Proceedings of The Tenth International Conference on Learning Representations."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.34"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","volume":"1","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)."},{"key":"e_1_3_2_1_8_1","volume-title":"Qizhe Xie, and Junxian He.","author":"Duan Keyu","year":"2023","unstructured":"Keyu Duan, Qian Liu, Tat-Seng Chua, Shuicheng Yan, Wei Tsang Ooi, Qizhe Xie, and Junxian He. 2023. Simteg: A frustratingly simple approach improves textual graph learning. arXiv preprint arXiv:2308.02565 (2023)."},{"key":"e_1_3_2_1_9_1","volume-title":"Proceedings of the 31th Annual Conference on Neural Information Processing Systems.","author":"Hamilton Will","year":"2017","unstructured":"Will Hamilton, Zhitao Ying, and Jure Leskovec. 2017. Inductive representation learning on large graphs. In Proceedings of the 31th Annual Conference on Neural Information Processing Systems."},{"key":"e_1_3_2_1_10_1","volume-title":"Proceedings of the 12th International Conference on Learning Representations.","author":"He Xiaoxin","year":"2024","unstructured":"Xiaoxin He, Xavier Bresson, Thomas Laurent, Adam Perold, Yann LeCun, and Bryan Hooi. 2024. Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation Learning. In Proceedings of the 12th International Conference on Learning Representations."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1031"},{"key":"e_1_3_2_1_12_1","volume-title":"Proceedings of the 34th Annual Conference on Neural Information Processing Systems.","author":"Hu Weihua","year":"2020","unstructured":"Weihua Hu, Matthias Fey, Marinka Zitnik, Yuxiao Dong, Hongyu Ren, Bowen Liu, Michele Catasta, and Jure Leskovec. 2020. Open graph benchmark: Datasets for machine learning on graphs. In Proceedings of the 34th Annual Conference on Neural Information Processing Systems."},{"key":"e_1_3_2_1_13_1","unstructured":"Albert Qiaochu Jiang Alexandre Sablayrolles Arthur Mensch Chris Bamford Devendra Singh Chaplot Diego de Las Casas Florian Bressand Gianna Lengyel Guillaume Lample Lucile Saulnier L'elio Renard Lavaud Marie-Anne Lachaux Pierre Stock Teven Le Scao Thibaut Lavril Thomas Wang Timoth\u00e9e Lacroix and William El Sayed. 2023. Mistral 7B. ArXiv (2023)."},{"key":"e_1_3_2_1_14_1","volume-title":"Proceedings of the 5th International Conference on Learning Representations.","author":"Kipf Thomas N","year":"2017","unstructured":"Thomas N Kipf and MaxWelling. 2017. Semi-supervised classification with graph convolutional networks. In Proceedings of the 5th International Conference on Learning Representations."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-55753-3_11"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3271675"},{"key":"e_1_3_2_1_17_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning.","author":"Li Guohao","year":"2021","unstructured":"Guohao Li, Matthias M\u00fcller, Bernard Ghanem, and Vladlen Koltun. 2021. Training graph neural networks with 1000 layers. In Proceedings of the 38th International Conference on Machine Learning."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43418-1_10"},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings of the 27th Annual Conference on Neural Information Processing Systems.","author":"Mikolov Tomas","year":"2013","unstructured":"Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Distributed Representations of Words and Phrases and their Compositionality. In Proceedings of the 27th Annual Conference on Neural Information Processing Systems."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_3_2_1_21_1","volume-title":"Collective classification in network data. AI magazine","author":"Sen Prithviraj","year":"2008","unstructured":"Prithviraj Sen, Galileo Namata, Mustafa Bilgic, Lise Getoor, Brian Galligher, and Tina Eliassi-Rad. 2008. Collective classification in network data. AI magazine (2008)."},{"key":"e_1_3_2_1_22_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, et al. 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_1_23_1","volume-title":"Proceedings of the 6th International Conference on Learning Representations.","author":"Velickovic Petar","year":"2018","unstructured":"Petar Velickovic, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, Yoshua Bengio, et al. 2018. Graph attention networks. In Proceedings of the 6th International Conference on Learning Representations."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.642"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611977653.ch19"},{"key":"e_1_3_2_1_26_1","volume-title":"Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval.","author":"Yuan Fang ZhihaoWen","year":"2023","unstructured":"ZhihaoWen and Yuan Fang. 2023. Augmenting Low-Resource Text Classification with Graph-Grounded Pre-training and Prompting. In Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval."},{"key":"e_1_3_2_1_27_1","volume-title":"A comparative study of open-source large language models, gpt-4 and claude 2: Multiple-choice test taking in nephrology. arXiv preprint arXiv:2308.04709","author":"Wu Sean","year":"2023","unstructured":"Sean Wu, Michael Koo, Lesley Blum, Andy Black, Liyo Kao, Fabien Scalzo, and Ira Kurtz. 2023. A comparative study of open-source large language models, gpt-4 and claude 2: Multiple-choice test taking in nephrology. arXiv preprint arXiv:2308.04709 (2023)."},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings of the 7th International Conference on Learning Representations.","author":"Xu Keyulu","year":"2019","unstructured":"Keyulu Xu,Weihua Hu, Jure Leskovec, and Stefanie Jegelka. 2019. How powerful are graph neural networks?. In Proceedings of the 7th International Conference on Learning Representations."},{"key":"e_1_3_2_1_29_1","volume-title":"Proceedings of the 37th Annual Conference on Neural Information Processing Systems.","author":"Yan Hao","year":"2023","unstructured":"Hao Yan, Chaozhuo Li, Ruosong Long, Chao Yan, Jianan Zhao, Wenwen Zhuang, Jun Yin, Peiyan Zhang, Weihao Han, Hao Sun, et al. 2023. A Comprehensive Study on Text-attributed Graphs: Benchmarking and Rethinking. In Proceedings of the 37th Annual Conference on Neural Information Processing Systems."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43415-0_41"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3132847.3132975"},{"key":"e_1_3_2_1_32_1","volume-title":"Proceedings of the 35th Annual Conference on Neural Information Processing Systems.","author":"Yang Junhan","year":"2021","unstructured":"Junhan Yang, Zheng Liu, Shitao Xiao, Chaozhuo Li, Defu Lian, Sanjay Agrawal, Amit Singh, Guangzhong Sun, and Xing Xie. 2021. GraphFormers: GNN-nested transformers for representation learning on textual graph. In Proceedings of the 35th Annual Conference on Neural Information Processing Systems."},{"key":"e_1_3_2_1_33_1","volume-title":"Proceedings of the 37th Annual Conference on Neural Information Processing Systems.","author":"Yin Jun","year":"2023","unstructured":"Jun Yin, Chaozhuo Li, Hao Yan, Jianxun Lian, and Senzhang Wang. 2023. Train once and explain everywhere: Pre-training interpretable graph neural networks. In Proceedings of the 37th Annual Conference on Neural Information Processing Systems."},{"key":"e_1_3_2_1_34_1","volume-title":"Proceedings of the 16th ACM international conference on web search and data mining.","author":"Zhang Peiyan","year":"2023","unstructured":"Peiyan Zhang, Jiayan Guo, Chaozhuo Li, Yueqi Xie, Jae Boum Kim, Yan Zhang, Xing Xie, Haohan Wang, and Sunghun Kim. 2023. Efficiently leveraging multilevel user intent for session-based recommendation via atten-mixer network. In Proceedings of the 16th ACM international conference on web search and data mining."},{"key":"e_1_3_2_1_35_1","volume-title":"Gophormer: Ego-graph transformer for node classification. arXiv preprint arXiv:2110.13094","author":"Zhao Jianan","year":"2021","unstructured":"Jianan Zhao, Chaozhuo Li, Qianlong Wen, Yiqi Wang, Yuming Liu, Hao Sun, Xing Xie, and Yanfang Ye. 2021. Gophormer: Ego-graph transformer for node classification. arXiv preprint arXiv:2110.13094 (2021)."},{"key":"e_1_3_2_1_36_1","volume-title":"Proceedings of the 11th International Conference on Learning Representations.","author":"Zhao Jianan","year":"2023","unstructured":"Jianan Zhao, Meng Qu, Chaozhuo Li, Hao Yan, Qian Liu, Rui Li, Xing Xie, and Jian Tang. 2023. Learning on Large-scale Text-attributed Graphs via Variational Inference. In Proceedings of the 11th International Conference on Learning Representations."},{"key":"e_1_3_2_1_37_1","unstructured":"Wayne Xin Zhao Kun Zhou Junyi Li Tianyi Tang Xiaolei Wang Yupeng Hou Yingqian Min Beichen Zhang Junjie Zhang Zican Dong et al. 2023. A survey of large language models. arXiv preprint arXiv:2303.18223 (2023)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591642"}],"event":{"name":"WSDM '25: The Eighteenth ACM International Conference on Web Search and Data Mining","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Hannover Germany","acronym":"WSDM '25"},"container-title":["Proceedings of the Eighteenth ACM International Conference on Web Search and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3701551.3703571","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3701551.3703571","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T09:13:48Z","timestamp":1755767628000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3701551.3703571"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,10]]},"references-count":38,"alternative-id":["10.1145\/3701551.3703571","10.1145\/3701551"],"URL":"https:\/\/doi.org\/10.1145\/3701551.3703571","relation":{},"subject":[],"published":{"date-parts":[[2025,3,10]]},"assertion":[{"value":"2025-03-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}