{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:40:56Z","timestamp":1786120856670,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T00:00:00Z","timestamp":1786147200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"National Natural Science Foundation of China","award":["62476245"],"award-info":[{"award-number":["62476245"]}]},{"name":"Alibaba Innovative Research Program","award":["N\/A"],"award-info":[{"award-number":["N\/A"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770855.3818177","type":"proceedings-article","created":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T17:15:47Z","timestamp":1786036547000},"page":"5256-5267","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Towards Next Graph Token Prediction: Discrete Graph Tokenization for Structural Reasoning in Large Language Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-2662-3415","authenticated-orcid":false,"given":"Zhonghao","family":"Wang","sequence":"first","affiliation":[{"name":"Zhejiang Key Lab of Accessible Perception and Intelligent Systems, Zhejiang University, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4824-9684","authenticated-orcid":false,"given":"Yugang","family":"Ji","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7326-7945","authenticated-orcid":false,"given":"Zhuonan","family":"Zheng","sequence":"additional","affiliation":[{"name":"Zhejiang Key Lab of Accessible Perception and Intelligent Systems, Zhejiang University, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3645-1041","authenticated-orcid":false,"given":"Sheng","family":"Zhou","sequence":"additional","affiliation":[{"name":"Zhejiang Key Lab of Accessible Perception and Intelligent Systems, Zhejiang University, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4597-6053","authenticated-orcid":false,"given":"Weigao","family":"Wen","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5447-9069","authenticated-orcid":false,"given":"Minghao","family":"Li","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2951-5256","authenticated-orcid":false,"given":"Ming","family":"Gu","sequence":"additional","affiliation":[{"name":"Zhejiang Key Lab of Accessible Perception and Intelligent Systems, Zhejiang University, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9291-169X","authenticated-orcid":false,"given":"Zhiyao","family":"Zhou","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1097-2044","authenticated-orcid":false,"given":"Jiajun","family":"Bu","sequence":"additional","affiliation":[{"name":"Zhejiang Key Lab of Accessible Perception and Intelligent Systems, Zhejiang University, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,8]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Graphlets as Building Blocks for Structural Vocabulary in Knowledge Graph Foundation Models. arXiv preprint arXiv:2605.06154","author":"Amouzouvi Kossi","year":"2026","unstructured":"Kossi Amouzouvi, Robert Wardenga, Jens Lehmann, and Sahar Vahdati. 2026. Graphlets as Building Blocks for Structural Vocabulary in Knowledge Graph Foundation Models. arXiv preprint arXiv:2605.06154 (2026)."},{"key":"e_1_3_2_1_2_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. Advances in neural information processing systems Vol. 33 (2020) 1877-1901."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3672010"},{"key":"e_1_3_2_1_4_1","volume-title":"Proceedings of the 41st International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"7823","author":"Chen Runjin","year":"2024","unstructured":"Runjin Chen, Tong Zhao, Ajay Kumar Jaiswal, Neil Shah, and Zhangyang Wang. 2024c. LLaGA: Large Language and Graph Assistant. In Proceedings of the 41st International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 235), Ruslan Salakhutdinov, Zico Kolter, Katherine Heller, Adrian Weller, Nuria Oliver, Jonathan Scarlett, and Felix Berkenkamp (Eds.). PMLR, 7809-7823."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657747"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2004.75"},{"key":"e_1_3_2_1_7_1","unstructured":"Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Amy Yang Angela Fan et al. 2024. The llama 3 herd of models. arXiv e-prints (2024) arXiv-2407."},{"key":"e_1_3_2_1_8_1","unstructured":"Paul Erd\u0151s Alfr\u00e9d R\u00e9nyi et al. 1960. On the evolution of random graphs. Publications of the (1960)."},{"key":"e_1_3_2_1_9_1","volume-title":"The Twelfth International Conference on Learning Representations.","author":"Fatemi Bahare","unstructured":"Bahare Fatemi, Jonathan Halcrow, and Bryan Perozzi. [n.d.]. Talk like a Graph: Encoding Graphs for Large Language Models. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_1_10_1","unstructured":"Daya Guo Dejian Yang Haowei Zhang Junxiao Song Ruoyu Zhang Runxin Xu Qihao Zhu Shirong Ma Peiyi Wang Xiao Bi et al. 2025. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. arXiv preprint arXiv:2501.12948 (2025)."},{"key":"e_1_3_2_1_11_1","volume-title":"Gpt4graph: Can large language models understand graph structured data? an empirical evaluation and benchmarking. arXiv preprint arXiv:2305.15066","author":"Guo Jiayan","year":"2023","unstructured":"Jiayan Guo, Lun Du, Hengyu Liu, Mengyu Zhou, Xinyi He, and Shi Han. 2023. Gpt4graph: Can large language models understand graph structured data? an empirical evaluation and benchmarking. arXiv preprint arXiv:2305.15066 (2023)."},{"key":"e_1_3_2_1_12_1","volume-title":"The Exploration in AI Today Workshop at ICML","author":"Guo Xiaojun","year":"2025","unstructured":"Xiaojun Guo, Ang Li, Yifei Wang, Stefanie Jegelka, and Yisen Wang. [n.d.]. G1: Teaching LLMs to Reason on Graphs with Reinforcement Learning. In The Exploration in AI Today Workshop at ICML 2025."},{"key":"e_1_3_2_1_13_1","volume-title":"Inductive representation learning on large graphs. Advances in neural information processing systems","author":"Hamilton Will","year":"2017","unstructured":"Will Hamilton, Zhitao Ying, and Jure Leskovec. 2017. Inductive representation learning on large graphs. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_14_1","unstructured":"Aaron Hurst Adam Lerer Adam P Goucher Adam Perelman Aditya Ramesh Aidan Clark AJ Ostrow Akila Welihinda Alan Hayes Alec Radford et al. 2024. Gpt-4o system card. arXiv preprint arXiv:2410.21276 (2024)."},{"key":"e_1_3_2_1_15_1","volume-title":"Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907","author":"Kipf TN","year":"2016","unstructured":"TN Kipf. 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)."},{"key":"e_1_3_2_1_16_1","volume-title":"GOFA: A Generative One-For-All Model for Joint Graph Language Modeling. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=mIjblC9hfm","author":"Kong Lecheng","year":"2025","unstructured":"Lecheng Kong, Jiarui Feng, Hao Liu, Chengsong Huang, Jiaxin Huang, Yixin Chen, and Muhan Zhang. 2025. GOFA: A Generative One-For-All Model for Joint Graph Language Modeling. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=mIjblC9hfm"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASONAM49781.2020.9381337"},{"key":"e_1_3_2_1_18_1","volume-title":"Graphteam: Facilitating large language model-based graph analysis via multi-agent collaboration. arXiv preprint arXiv:2410.18032","author":"Li Xin","year":"2024","unstructured":"Xin Li, Qizhi Chu, Yubin Chen, Yang Liu, Yaoqi Liu, Zekai Yu, Weize Chen, Chen Qian, Chuan Shi, and Cheng Yang. 2024. Graphteam: Facilitating large language model-based graph analysis via multi-agent collaboration. arXiv preprint arXiv:2410.18032 (2024)."},{"key":"e_1_3_2_1_19_1","volume-title":"Visual instruction tuning. Advances in neural information processing systems","author":"Liu Haotian","year":"2023","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023. Visual instruction tuning. Advances in neural information processing systems, Vol. 36 (2023), 34892-34916."},{"key":"e_1_3_2_1_20_1","first-page":"824","volume-title":"Science","volume":"298","author":"Milo Ron","year":"2002","unstructured":"Ron Milo, Shai Shen-Orr, Shalev Itzkovitz, Nadav Kashtan, Dmitri Chklovskii, and Uri Alon. 2002. Network motifs: simple building blocks of complex networks. Science, Vol. 298, 5594 (2002), 824-827."},{"key":"e_1_3_2_1_21_1","volume-title":"Tudataset: A collection of benchmark datasets for learning with graphs. arXiv preprint arXiv:2007.08663","author":"Morris Christopher","year":"2020","unstructured":"Christopher Morris, Nils M Kriege, Franka Bause, Kristian Kersting, Petra Mutzel, and Marion Neumann. 2020. Tudataset: A collection of benchmark datasets for learning with graphs. arXiv preprint arXiv:2007.08663 (2020)."},{"key":"e_1_3_2_1_22_1","volume-title":"Unsupervised Graph Anomaly Detection via Multi-Hypersphere Heterophilic Graph Learning. arXiv preprint arXiv:2503.12037","author":"Ni Hang","year":"2025","unstructured":"Hang Ni, Jindong Han, Nengjun Zhu, and Hao Liu. 2025. Unsupervised Graph Anomaly Detection via Multi-Hypersphere Heterophilic Graph Learning. arXiv preprint arXiv:2503.12037 (2025)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btl301"},{"key":"e_1_3_2_1_24_1","volume-title":"Direct preference optimization: Your language model is secretly a reward model. Advances in neural information processing systems","author":"Rafailov Rafael","year":"2023","unstructured":"Rafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D Manning, Stefano Ermon, and Chelsea Finn. 2023. Direct preference optimization: Your language model is secretly a reward model. Advances in neural information processing systems, Vol. 36 (2023), 53728-53741."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3406703"},{"key":"e_1_3_2_1_26_1","volume-title":"Ankur Bapna, Zal\u00e1n Borsos, F\u00e9lix de Chaumont Quitry, Peter Chen, Dalia El Badawy, Wei Han, Eugene Kharitonov, et al.","author":"Rubenstein Paul K","year":"2023","unstructured":"Paul K Rubenstein, Chulayuth Asawaroengchai, Duc Dung Nguyen, Ankur Bapna, Zal\u00e1n Borsos, F\u00e9lix de Chaumont Quitry, Peter Chen, Dalia El Badawy, Wei Han, Eugene Kharitonov, et al., 2023. Audiopalm: A large language model that can speak and listen. arXiv preprint arXiv:2306.12925 (2023)."},{"key":"e_1_3_2_1_27_1","volume-title":"Deepseekmath: Pushing the limits of mathematical reasoning in open language models. arXiv preprint arXiv:2402.03300","author":"Shao Zhihong","year":"2024","unstructured":"Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Xiao Bi, Haowei Zhang, Mingchuan Zhang, YK Li, Yang Wu, et al., 2024. Deepseekmath: Pushing the limits of mathematical reasoning in open language models. arXiv preprint arXiv:2402.03300 (2024)."},{"key":"e_1_3_2_1_28_1","first-page":"488","article-title":"Efficient graphlet kernels for large graph comparison. In Artificial intelligence and statistics","author":"Shervashidze Nino","year":"2009","unstructured":"Nino Shervashidze, SVN Vishwanathan, Tobias Petri, Kurt Mehlhorn, and Karsten Borgwardt. 2009. Efficient graphlet kernels for large graph comparison. In Artificial intelligence and statistics. PMLR, 488-495.","journal-title":"PMLR"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671987"},{"key":"e_1_3_2_1_30_1","volume-title":"GraphArena: Evaluating and Exploring Large Language Models on Graph Computation. In The Thirteenth International Conference on Learning Representations.","author":"Tang Jianheng","unstructured":"Jianheng Tang, Qifan Zhang, Yuhan Li, Nuo Chen, and Jia Li. [n.d.]. GraphArena: Evaluating and Exploring Large Language Models on Graph Computation. In The Thirteenth International Conference on Learning Representations."},{"key":"e_1_3_2_1_31_1","first-page":"30840","volume-title":"Levine (Eds.)","volume":"36","author":"Wang Heng","year":"2023","unstructured":"Heng Wang, Shangbin Feng, Tianxing He, Zhaoxuan Tan, Xiaochuang Han, and Yulia Tsvetkov. 2023. Can Language Models Solve Graph Problems in Natural Language?. In Advances in Neural Information Processing Systems, A. Oh, T. Naumann, A. Globerson, K. Saenko, M. Hardt, and S. Levine (Eds.), Vol. 36. Curran Associates, Inc., 30840-30861."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.801"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3412"},{"key":"e_1_3_2_1_34_1","volume-title":"Collective dynamics of 'small-world'networks. nature","author":"Watts Duncan J","year":"1998","unstructured":"Duncan J Watts and Steven H Strogatz. 1998. Collective dynamics of 'small-world'networks. nature, Vol. 393, 6684 (1998), 440-442."},{"key":"e_1_3_2_1_35_1","unstructured":"Jason Wei Yi Tay Rishi Bommasani Colin Raffel Barret Zoph Sebastian Borgeaud Dani Yogatama Maarten Bosma Denny Zhou Donald Metzler et al. 2022. Emergent abilities of large language models. arXiv preprint arXiv:2206.07682 (2022)."},{"key":"e_1_3_2_1_36_1","first-page":"12","article-title":"The reduction of a graph to canonical form and the algebra which appears therein. nti","volume":"2","author":"Weisfeiler Boris","year":"1968","unstructured":"Boris Weisfeiler and Andrei Leman. 1968. The reduction of a graph to canonical form and the algebra which appears therein. nti, Series, Vol. 2, 9 (1968), 12-16.","journal-title":"Series"},{"key":"e_1_3_2_1_37_1","volume-title":"International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=ryGs6iA5Km","author":"Xu Keyulu","year":"2019","unstructured":"Keyulu Xu, Weihua Hu, Jure Leskovec, and Stefanie Jegelka. 2019. How Powerful are Graph Neural Networks?. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=ryGs6iA5Km"},{"key":"e_1_3_2_1_38_1","unstructured":"An Yang Anfeng Li Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chang Gao Chengen Huang Chenxu Lv et al. 2025. Qwen3 technical report. arXiv preprint arXiv:2505.09388 (2025)."},{"key":"e_1_3_2_1_39_1","volume-title":"GRAVER: Generative Graph Vocabularies for Robust Graph Foundation Models Fine-tuning. arXiv preprint arXiv:2511.05592","author":"Yuan Haonan","year":"2025","unstructured":"Haonan Yuan, Qingyun Sun, Junhua Shi, Xingcheng Fu, Bryan Hooi, Jianxin Li, and Philip S Yu. 2025. GRAVER: Generative Graph Vocabularies for Robust Graph Foundation Models Fine-tuning. arXiv preprint arXiv:2511.05592 (2025)."},{"key":"e_1_3_2_1_40_1","volume-title":"Graph transformer networks. Advances in neural information processing systems","author":"Yun Seongjun","year":"2019","unstructured":"Seongjun Yun, Minbyul Jeong, Raehyun Kim, Jaewoo Kang, and Hyunwoo J Kim. 2019. Graph transformer networks. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645682"},{"key":"e_1_3_2_1_42_1","volume-title":"Gcoder: Improving large language model for generalized graph problem solving. arXiv preprint arXiv:2410.19084","author":"Zhang Qifan","year":"2024","unstructured":"Qifan Zhang, Xiaobin Hong, Jianheng Tang, Nuo Chen, Yuhan Li, Wenzhong Li, Jing Tang, and Jia Li. 2024a. Gcoder: Improving large language model for generalized graph problem solving. arXiv preprint arXiv:2410.19084 (2024)."},{"key":"e_1_3_2_1_43_1","volume-title":"Can LLM Graph Reasoning Generalize beyond Pattern Memorization? arXiv preprint arXiv:2406.15992","author":"Zhang Yizhuo","year":"2024","unstructured":"Yizhuo Zhang, Heng Wang, Shangbin Feng, Zhaoxuan Tan, Xiaochuang Han, Tianxing He, and Yulia Tsvetkov. 2024c. Can LLM Graph Reasoning Generalize beyond Pattern Memorization? arXiv preprint arXiv:2406.15992 (2024)."},{"key":"e_1_3_2_1_44_1","volume-title":"Each Graph is a New Language: Graph Learning with LLMs. arXiv preprint arXiv:2501.11478","author":"Zhou Huachi","year":"2025","unstructured":"Huachi Zhou, Jiahe Du, Chuang Zhou, Chang Yang, Yilin Xiao, Yuxuan Xie, and Xiao Huang. 2025. Each Graph is a New Language: Graph Learning with LLMs. arXiv preprint arXiv:2501.11478 (2025)."},{"key":"e_1_3_2_1_45_1","volume-title":"Llm as gnn: Graph vocabulary learning for text-attributed graph foundation models. arXiv preprint arXiv:2503.03313","author":"Zhu Xi","year":"2025","unstructured":"Xi Zhu, Haochen Xue, Ziwei Zhao, Wujiang Xu, Jingyuan Huang, Minghao Guo, Qifan Wang, Kaixiong Zhou, Imran Razzak, and Yongfeng Zhang. 2025. Llm as gnn: Graph vocabulary learning for text-attributed graph foundation models. arXiv preprint arXiv:2503.03313 (2025)."}],"event":{"name":"KDD '26: The 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Jeju Island Republic of Korea","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T01:19:13Z","timestamp":1786065553000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3818177"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":45,"alternative-id":["10.1145\/3770855.3818177","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3818177","relation":{},"subject":[],"published":{"date-parts":[[2026,8,8]]},"assertion":[{"value":"2026-08-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}