{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T10:07:46Z","timestamp":1775815666608,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T00:00:00Z","timestamp":1729468800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["No. 1755850, No. 1841520, No. 1942594, No. 2403312, No. 2007716, No. 2007976, No. 1942594, No. No. 1907805"],"award-info":[{"award-number":["No. 1755850, No. 1841520, No. 1942594, No. 2403312, No. 2007716, No. 2007976, No. 1942594, No. No. 1907805"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,21]]},"DOI":"10.1145\/3627673.3679830","type":"proceedings-article","created":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T19:34:11Z","timestamp":1729452851000},"page":"1836-1845","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["Distilling Large Language Models for Text-Attributed Graph Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-7501-7581","authenticated-orcid":false,"given":"Bo","family":"Pan","sequence":"first","affiliation":[{"name":"Emory University, Atlanta, GA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9808-6020","authenticated-orcid":false,"given":"Zheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Emory University, Atlanta, GA, GA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6136-733X","authenticated-orcid":false,"given":"Yifei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Emory University, Atlanta, GA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3802-9039","authenticated-orcid":false,"given":"Yuntong","family":"Hu","sequence":"additional","affiliation":[{"name":"Emory University, Atlanta, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2648-9989","authenticated-orcid":false,"given":"Liang","family":"Zhao","sequence":"additional","affiliation":[{"name":"Emory University, Atlanta, GA, USA"}]}],"member":"320","published-online":{"date-parts":[[2024,10,21]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Guangji Bai Zheng Chai Chen Ling Shiyu Wang Jiaying Lu Nan Zhang Tingwei Shi Ziyang Yu Mengdan Zhu Yifei Zhang et al. 2024. Beyond efficiency: A systematic survey of resource-efficient large language models. arXiv preprint arXiv:2401.00625 (2024)."},{"key":"e_1_3_2_1_2_1","volume-title":"LLaGA: Large Language and Graph Assistant. arXiv preprint arXiv:2402.08170","author":"Chen Runjin","year":"2024","unstructured":"Runjin Chen, Tong Zhao, Ajay Jaiswal, Neil Shah, and Zhangyang Wang. 2024. LLaGA: Large Language and Graph Assistant. arXiv preprint arXiv:2402.08170 (2024)."},{"key":"e_1_3_2_1_3_1","unstructured":"Zhikai Chen Haitao Mao Hang Li Wei Jin Hongzhi Wen Xiaochi Wei Shuaiqiang Wang Dawei Yin Wenqi Fan Hui Liu et al. 2023. Exploring the potential of large language models (llms) in learning on graphs. arXiv preprint arXiv:2307.03393 (2023)."},{"key":"e_1_3_2_1_4_1","volume-title":"Label-free node classification on graphs with large language models (llms). arXiv preprint arXiv:2310.04668","author":"Chen Zhikai","year":"2023","unstructured":"Zhikai Chen, Haitao Mao, Hongzhi Wen, Haoyu Han, Wei Jin, Haiyang Zhang, Hui Liu, and Jiliang Tang. 2023. Label-free node classification on graphs with large language models (llms). arXiv preprint arXiv:2310.04668 (2023)."},{"key":"e_1_3_2_1_5_1","volume-title":"Node feature extraction by self-supervised multi-scale neighborhood prediction. arXiv preprint arXiv:2111.00064","author":"Chien Eli","year":"2021","unstructured":"Eli Chien, Wei-Cheng Chang, Cho-Jui Hsieh, Hsiang-Fu Yu, Jiong Zhang, Olgica Milenkovic, and Inderjit S Dhillon. 2021. Node feature extraction by self-supervised multi-scale neighborhood prediction. arXiv preprint arXiv:2111.00064 (2021)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.463"},{"key":"e_1_3_2_1_7_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"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":"Fast Graph Representation Learning with PyTorch Geometric. In ICLR Workshop on Representation Learning on Graphs and Manifolds.","author":"Fey Matthias","unstructured":"Matthias Fey and Jan E. Lenssen. 2019. Fast Graph Representation Learning with PyTorch Geometric. In ICLR Workshop on Representation Learning on Graphs and Manifolds."},{"key":"e_1_3_2_1_10_1","volume-title":"XAI-CLASS: Explanation-Enhanced Text Classification with Extremely Weak Supervision. arXiv preprint arXiv:2311.00189","author":"Hajialigol Daniel","year":"2023","unstructured":"Daniel Hajialigol, Hanwen Liu, and Xuan Wang. 2023. XAI-CLASS: Explanation-Enhanced Text Classification with Extremely Weak Supervision. arXiv preprint arXiv:2311.00189 (2023)."},{"key":"e_1_3_2_1_11_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_12_1","volume-title":"Deberta: Decoding-enhanced bert with disentangled attention. arXiv preprint arXiv:2006.03654","author":"He Pengcheng","year":"2020","unstructured":"Pengcheng He, Xiaodong Liu, Jianfeng Gao, and Weizhu Chen. 2020. Deberta: Decoding-enhanced bert with disentangled attention. arXiv preprint arXiv:2006.03654 (2020)."},{"key":"e_1_3_2_1_13_1","volume-title":"Explanations as Features: LLM-Based Features for Text-Attributed Graphs. arXiv preprint arXiv:2305.19523","author":"He Xiaoxin","year":"2023","unstructured":"Xiaoxin He, Xavier Bresson, Thomas Laurent, and Bryan Hooi. 2023. Explanations as Features: LLM-Based Features for Text-Attributed Graphs. arXiv preprint arXiv:2305.19523 (2023)."},{"key":"e_1_3_2_1_14_1","volume-title":"Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531","author":"Hinton Geoffrey","year":"2015","unstructured":"Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. 2015. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)."},{"key":"e_1_3_2_1_15_1","volume-title":"Large language models are reasoning teachers. arXiv preprint arXiv:2212.10071","author":"Ho Namgyu","year":"2022","unstructured":"Namgyu Ho, Laura Schmid, and Se-Young Yun. 2022. Large language models are reasoning teachers. arXiv preprint arXiv:2212.10071 (2022)."},{"key":"e_1_3_2_1_16_1","volume-title":"Distilling step-by-step! outperforming larger language models with less training data and smaller model sizes. arXiv preprint arXiv:2305.02301","author":"Hsieh Cheng-Yu","year":"2023","unstructured":"Cheng-Yu Hsieh, Chun-Liang Li, Chih-Kuan Yeh, Hootan Nakhost, Yasuhisa Fujii, Alexander Ratner, Ranjay Krishna, Chen-Yu Lee, and Tomas Pfister. 2023. Distilling step-by-step! outperforming larger language models with less training data and smaller model sizes. arXiv preprint arXiv:2305.02301 (2023)."},{"key":"e_1_3_2_1_17_1","volume-title":"Open graph benchmark: Datasets for machine learning on graphs. Advances in 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. Advances in neural information processing systems, Vol. 33 (2020), 22118--22133."},{"key":"e_1_3_2_1_18_1","volume-title":"Beyond Text: A Deep Dive into Large Language Models' Ability on Understanding Graph Data. arXiv preprint arXiv:2310.04944","author":"Hu Yuntong","year":"2023","unstructured":"Yuntong Hu, Zheng Zhang, and Liang Zhao. 2023. Beyond Text: A Deep Dive into Large Language Models' Ability on Understanding Graph Data. arXiv preprint arXiv:2310.04944 (2023)."},{"key":"e_1_3_2_1_19_1","volume-title":"Can llms effectively leverage graph structural information: when and why. arXiv preprint arXiv:2309.16595","author":"Huang Jin","year":"2023","unstructured":"Jin Huang, Xingjian Zhang, Qiaozhu Mei, and Jiaqi Ma. 2023. Can llms effectively leverage graph structural information: when and why. arXiv preprint arXiv:2309.16595 (2023)."},{"key":"e_1_3_2_1_20_1","volume-title":"Tinybert: Distilling bert for natural language understanding. arXiv preprint arXiv:1909.10351","author":"Jiao Xiaoqi","year":"2019","unstructured":"Xiaoqi Jiao, Yichun Yin, Lifeng Shang, Xin Jiang, Xiao Chen, Linlin Li, Fang Wang, and Qun Liu. 2019. Tinybert: Distilling bert for natural language understanding. arXiv preprint arXiv:1909.10351 (2019)."},{"key":"e_1_3_2_1_21_1","volume-title":"Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907","author":"Kipf Thomas N","year":"2016","unstructured":"Thomas N Kipf and Max Welling. 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)."},{"key":"e_1_3_2_1_22_1","volume-title":"Symbolic Chain-of-Thought Distillation: Small Models Can Also\" Think\" Step-by-Step. arXiv preprint arXiv:2306.14050","author":"Li Liunian Harold","year":"2023","unstructured":"Liunian Harold Li, Jack Hessel, Youngjae Yu, Xiang Ren, Kai-Wei Chang, and Yejin Choi. 2023. Symbolic Chain-of-Thought Distillation: Small Models Can Also\" Think\" Step-by-Step. arXiv preprint arXiv:2306.14050 (2023)."},{"key":"e_1_3_2_1_23_1","unstructured":"Shiyang Li Jianshu Chen Yelong Shen Zhiyu Chen Xinlu Zhang Zekun Li Hong Wang Jing Qian Baolin Peng Yi Mao et al. 2022. Explanations from large language models make small reasoners better. arXiv preprint arXiv:2210.06726 (2022)."},{"key":"e_1_3_2_1_24_1","volume-title":"Unifying distillation and privileged information. arXiv preprint arXiv:1511.03643","author":"Lopez-Paz David","year":"2015","unstructured":"David Lopez-Paz, L\u00e9on Bottou, Bernhard Sch\u00f6lkopf, and Vladimir Vapnik. 2015. Unifying distillation and privileged information. arXiv preprint arXiv:1511.03643 (2015)."},{"key":"e_1_3_2_1_25_1","volume-title":"Teaching small language models to reason. arXiv preprint arXiv:2212.08410","author":"Magister Lucie Charlotte","year":"2022","unstructured":"Lucie Charlotte Magister, Jonathan Mallinson, Jakub Adamek, Eric Malmi, and Aliaksei Severyn. 2022. Teaching small language models to reason. arXiv preprint arXiv:2212.08410 (2022)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1009953814988"},{"key":"e_1_3_2_1_27_1","volume-title":"a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108","author":"Sanh Victor","year":"2019","unstructured":"Victor Sanh, Lysandre Debut, Julien Chaumond, and Thomas Wolf. 2019. DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108 (2019)."},{"key":"e_1_3_2_1_28_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, Vol. 29, 3 (2008), 93--93."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.441"},{"key":"e_1_3_2_1_30_1","volume-title":"Large Language Models as Topological Structure Enhancers for Text-Attributed Graphs. arXiv preprint arXiv:2311.14324","author":"Sun Shengyin","year":"2023","unstructured":"Shengyin Sun, Yuxiang Ren, Chen Ma, and Xuecang Zhang. 2023. Large Language Models as Topological Structure Enhancers for Text-Attributed Graphs. arXiv preprint arXiv:2311.14324 (2023)."},{"key":"e_1_3_2_1_31_1","volume-title":"Graphgpt: Graph instruction tuning for large language models. arXiv preprint arXiv:2310.13023","author":"Tang Jiabin","year":"2023","unstructured":"Jiabin Tang, Yuhao Yang, Wei Wei, Lei Shi, Lixin Su, Suqi Cheng, Dawei Yin, and Chao Huang. 2023. Graphgpt: Graph instruction tuning for large language models. arXiv preprint arXiv:2310.13023 (2023)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.5555\/2789272.2886814"},{"key":"e_1_3_2_1_33_1","volume-title":"Graph attention networks. arXiv preprint arXiv:1710.10903","author":"Velivckovic Petar","year":"2017","unstructured":"Petar Velivckovic, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, and Yoshua Bengio. 2017. Graph attention networks. arXiv preprint arXiv:1710.10903 (2017)."},{"key":"e_1_3_2_1_34_1","unstructured":"Zhongwei Wan Xin Wang Che Liu Samiul Alam Yu Zheng Zhongnan Qu Shen Yan Yi Zhu Quanlu Zhang Mosharaf Chowdhury et al. 2023. Efficient large language models: A survey. arXiv preprint arXiv:2312.03863 Vol. 1 (2023)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467230"},{"key":"e_1_3_2_1_36_1","first-page":"11815","article-title":"Knowledge distillation improves graph structure augmentation for graph neural networks","volume":"35","author":"Wu Lirong","year":"2022","unstructured":"Lirong Wu, Haitao Lin, Yufei Huang, and Stan Z Li. 2022. Knowledge distillation improves graph structure augmentation for graph neural networks. Advances in Neural Information Processing Systems, Vol. 35 (2022), 11815--11827.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_37_1","volume-title":"A survey on large language model (llm) security and privacy: The good, the bad, and the ugly. arXiv preprint arXiv:2312.02003","author":"Yao Yifan","year":"2023","unstructured":"Yifan Yao, Jinhao Duan, Kaidi Xu, Yuanfang Cai, Eric Sun, and Yue Zhang. 2023. A survey on large language model (llm) security and privacy: The good, the bad, and the ugly. arXiv preprint arXiv:2312.02003 (2023)."},{"key":"e_1_3_2_1_38_1","volume-title":"Findings of the Association for Computational Linguistics: EACL 2024. 1955","author":"Ye Ruosong","year":"2024","unstructured":"Ruosong Ye, Caiqi Zhang, Runhui Wang, Shuyuan Xu, and Yongfeng Zhang. 2024. Language is all a graph needs. In Findings of the Association for Computational Linguistics: EACL 2024. 1955--1973."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539316"},{"key":"e_1_3_2_1_40_1","volume-title":"Graph-less neural networks: Teaching old mlps new tricks via distillation. arXiv preprint arXiv:2110.08727","author":"Zhang Shichang","year":"2021","unstructured":"Shichang Zhang, Yozen Liu, Yizhou Sun, and Neil Shah. 2021. Graph-less neural networks: Teaching old mlps new tricks via distillation. arXiv preprint arXiv:2110.08727 (2021)."},{"key":"e_1_3_2_1_41_1","volume-title":"Visual Attention-Prompted Prediction and Learning. arXiv preprint arXiv:2310.08420","author":"Zhang Yifei","year":"2023","unstructured":"Yifei Zhang, Siyi Gu, Bo Pan, Guangji Bai, Xiaofeng Yang, and Liang Zhao. 2023. Visual Attention-Prompted Prediction and Learning. arXiv preprint arXiv:2310.08420 (2023)."},{"key":"e_1_3_2_1_42_1","volume-title":"ELAD: Explanation-Guided Large Language Models Active Distillation. arXiv preprint arXiv:2402.13098","author":"Zhang Yifei","year":"2024","unstructured":"Yifei Zhang, Bo Pan, Chen Ling, Yuntong Hu, and Liang Zhao. 2024. ELAD: Explanation-Guided Large Language Models Active Distillation. arXiv preprint arXiv:2402.13098 (2024)."},{"key":"e_1_3_2_1_43_1","volume-title":"TAGA: Text-Attributed Graph Self-Supervised Learning by Synergizing Graph and Text Mutual Transformations. arXiv preprint arXiv:2405.16800","author":"Zhang Zheng","year":"2024","unstructured":"Zheng Zhang, Yuntong Hu, Bo Pan, Chen Ling, and Liang Zhao. 2024. TAGA: Text-Attributed Graph Self-Supervised Learning by Synergizing Graph and Text Mutual Transformations. arXiv preprint arXiv:2405.16800 (2024)."},{"key":"e_1_3_2_1_44_1","volume-title":"Learning on large-scale text-attributed graphs via variational inference. arXiv preprint arXiv:2210.14709","author":"Zhao Jianan","year":"2022","unstructured":"Jianan Zhao, Meng Qu, Chaozhuo Li, Hao Yan, Qian Liu, Rui Li, Xing Xie, and Jian Tang. 2022. Learning on large-scale text-attributed graphs via variational inference. arXiv preprint arXiv:2210.14709 (2022)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449842"}],"event":{"name":"CIKM '24: The 33rd ACM International Conference on Information and Knowledge Management","location":"Boise ID USA","acronym":"CIKM '24","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 33rd ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627673.3679830","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3627673.3679830","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:58:07Z","timestamp":1750294687000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627673.3679830"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,21]]},"references-count":45,"alternative-id":["10.1145\/3627673.3679830","10.1145\/3627673"],"URL":"https:\/\/doi.org\/10.1145\/3627673.3679830","relation":{},"subject":[],"published":{"date-parts":[[2024,10,21]]},"assertion":[{"value":"2024-10-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}