Distilling Large Language Models for Text-Attributed Graph Learning
Pages 1836 - 1845
Abstract
Text-Attributed Graphs (TAGs) are graphs of connected textual documents. Graph models can efficiently learn TAGs, but their training heavily relies on human-annotated labels, which are scarce or even unavailable in many applications. Large language models (LLMs) have recently demonstrated remarkable capabilities in few-shot and zero-shot TAG learning, but they suffer from scalability, cost, and privacy issues. Therefore, in this work, we focus on synergizing LLMs and graph models with their complementary strengths by distilling the power of LLMs into a local graph model on TAG learning. To address the inherent gaps between LLMs (generative models for texts) and graph models (discriminative models for graphs), we propose first to let LLMs teach an interpreter with rich rationale and then let a student model mimic the interpreter's reasoning without LLMs' rationale. We convert LLM's textual rationales to multi-level graph rationales to train the interpreter model and align the student model with the interpreter model based on the features of TAGs. Extensive experiments validate the efficacy of our proposed framework.
References
[1]
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).
[2]
Runjin Chen, Tong Zhao, Ajay Jaiswal, Neil Shah, and Zhangyang Wang. 2024. LLaGA: Large Language and Graph Assistant. arXiv preprint arXiv:2402.08170 (2024).
[3]
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).
[4]
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).
[5]
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).
[6]
Sayantan Dasgupta, Trevor Cohn, and Timothy Baldwin. 2023. Cost-effective distillation of large language models. In Findings of the Association for Computational Linguistics: ACL 2023. 7346--7354.
[7]
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).
[8]
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).
[9]
Matthias Fey and Jan E. Lenssen. 2019. Fast Graph Representation Learning with PyTorch Geometric. In ICLR Workshop on Representation Learning on Graphs and Manifolds.
[10]
Daniel Hajialigol, Hanwen Liu, and Xuan Wang. 2023. XAI-CLASS: Explanation-Enhanced Text Classification with Extremely Weak Supervision. arXiv preprint arXiv:2311.00189 (2023).
[11]
Will Hamilton, Zhitao Ying, and Jure Leskovec. 2017. Inductive representation learning on large graphs. Advances in neural information processing systems, Vol. 30 (2017).
[12]
Pengcheng He, Xiaodong Liu, Jianfeng Gao, and Weizhu Chen. 2020. Deberta: Decoding-enhanced bert with disentangled attention. arXiv preprint arXiv:2006.03654 (2020).
[13]
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).
[14]
Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. 2015. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015).
[15]
Namgyu Ho, Laura Schmid, and Se-Young Yun. 2022. Large language models are reasoning teachers. arXiv preprint arXiv:2212.10071 (2022).
[16]
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).
[17]
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.
[18]
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).
[19]
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).
[20]
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).
[21]
Thomas N Kipf and Max Welling. 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016).
[22]
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).
[23]
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).
[24]
David Lopez-Paz, Léon Bottou, Bernhard Schölkopf, and Vladimir Vapnik. 2015. Unifying distillation and privileged information. arXiv preprint arXiv:1511.03643 (2015).
[25]
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).
[26]
Andrew Kachites McCallum, Kamal Nigam, Jason Rennie, and Kristie Seymore. 2000. Automating the construction of internet portals with machine learning. Information Retrieval, Vol. 3 (2000), 127--163.
[27]
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).
[28]
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.
[29]
Kumar Shridhar, Alessandro Stolfo, and Mrinmaya Sachan. 2023. Distilling reasoning capabilities into smaller language models. In Findings of the Association for Computational Linguistics: ACL 2023. 7059--7073.
[30]
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).
[31]
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).
[32]
Vladimir Vapnik, Rauf Izmailov, et al. 2015. Learning using privileged information: similarity control and knowledge transfer. J. Mach. Learn. Res., Vol. 16, 1 (2015), 2023--2049.
[33]
Petar Velivckovic, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, and Yoshua Bengio. 2017. Graph attention networks. arXiv preprint arXiv:1710.10903 (2017).
[34]
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).
[35]
Zheng Wang, Jialong Wang, Yuchen Guo, and Zhiguo Gong. 2021. Zero-shot node classification with decomposed graph prototype network. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. 1769--1779.
[36]
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.
[37]
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).
[38]
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.
[39]
Qin Yue, Jiye Liang, Junbiao Cui, and Liang Bai. 2022. Dual Bidirectional Graph Convolutional Networks for Zero-shot Node Classification. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 2408--2417.
[40]
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).
[41]
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).
[42]
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).
[43]
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).
[44]
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).
[45]
Jason Zhu, Yanling Cui, Yuming Liu, Hao Sun, Xue Li, Markus Pelger, Tianqi Yang, Liangjie Zhang, Ruofei Zhang, and Huasha Zhao. 2021. Textgnn: Improving text encoder via graph neural network in sponsored search. In Proceedings of the Web Conference 2021. 2848--2857.
Index Terms
- Distilling Large Language Models for Text-Attributed Graph Learning
Recommendations
GraphGPT: Graph Instruction Tuning for Large Language Models
SIGIR '24: Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information RetrievalGraph Neural Networks (GNNs) have evolved to understand graph structures through recursive exchanges and aggregations among nodes. To enhance robustness, self-supervised learning (SSL) has become a vital tool for data augmentation. Traditional methods ...
GAugLLM: Improving Graph Contrastive Learning for Text-Attributed Graphs with Large Language Models
KDD '24: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data MiningThis work studies self-supervised graph learning for text-attributed graphs (TAGs) where nodes are represented by textual attributes. Unlike traditional graph contrastive methods that perturb the numerical feature space and alter the graph's topological ...
Pre-Training and Prompting for Few-Shot Node Classification on Text-Attributed Graphs
KDD '24: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data MiningThe text-attributed graph (TAG) is one kind of important real-world graph-structured data with each node associated with raw texts. For TAGs, traditional few-shot node classification methods directly conduct training on the pre-processed node features ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
October 2024
5705 pages
Copyright © 2024 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Sponsors
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 21 October 2024
Check for updates
Author Tags
Qualifiers
- Research-article
Funding Sources
Conference
CIKM '24
Sponsor:
CIKM '24: The 33rd ACM International Conference on Information and Knowledge Management
October 21 - 25, 2024
ID, Boise, USA
Acceptance Rates
Overall Acceptance Rate 1,861 of 8,427 submissions, 22%
Upcoming Conference
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 239Total Downloads
- Downloads (Last 12 months)239
- Downloads (Last 6 weeks)155
Reflects downloads up to 21 Dec 2024
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in