Graph plays a significant role in representing and analyzing complex relationships in real-world applications such as citation networks, social networks, and biological data. Graph intelligence is rapidly becoming a crucial aspect of understanding and exploiting the intricate interconnections within graph data. Recently, large language models (LLMs) and prompt learning techniques have pushed graph intelligence forward, outperforming traditional Graph Neural Network (GNN) pre-training methods and setting new benchmarks for performance. In this tutorial, we begin by offering a comprehensive review and analysis of existing methods that integrate LLMs with graphs. We introduce existing works based on a novel taxonomy that classifies them into three distinct categories according to the roles of LLMs in graph tasks: as enhancers, predictors, or alignment components. Secondly, we introduce a new learning method that utilizes prompting on graphs, offering substantial potential to enhance graph transfer capabilities across diverse tasks and domains. We discuss existing works on graph prompting within a unified framework and introduce our developed tool for executing a variety of graph prompting tasks. Additionally, we discuss the applications of combining Graphs, LLMs, and prompt learning across various tasks, such as urban computing, recommendation systems, and anomaly detection. This lecture-style tutorial is an extension of our original work published in IJCAI 2024 and arXiv with the invitation of KDD24.
The tutorial will be held on August 25 10:00 - 13:00 UTC+1.
Jia Li is an assistant professor with the Data Science and Analytics Thrust, Information Hub,
The Hong Kong University of Science and Technology. He received the Ph.D. degree at The Chinese
University of Hong Kong in 2021. His research interests include machine learning, data mining and
deep graph learning. He received the KDD'23 best paper award and published several papers as the
leading/corresponding author in top conferences such as T-PAMI, KDD, NeurIPS and ICML.
Xiangguo Sun
is a postdoctoral research fellow at The Chinese University of Hong Kong. He was recognized as the
"Social Computing Rising Star" in 2023 by CAAI. He received his Ph.D. from Southeast University and
won the Distinguished Ph.D. Dissertation Award. He studied as a joint Ph.D. student at The University
of Queensland hosted by ARC Future Fellow Prof. Hongzhi Yin from Sep 2019 to Sep 2021. His research
interests include social computing and network learning. Some of his works appear in SIGKDD, ICLR, VLDB,
The Web Conference, TKDE, etc.
Yuhan Li is currently a second-year Ph.D. student of the Data Science and Analytics thrust, Hong
Kong University of Science and Technology (Guangzhou), supervised by Prof. Jia Li. He received the
master degree in Computer Science from Nankai University in 2023. His research interests mainly focus
on large language models and (knowledge) graph learning. He has published papers in international
conferences and journals, such as SIGKDD, EMNLP, IJCAI, and TKDE. He has also reviewed papers in many
top-tier conferences and journals, like SIGKDD, ACL, TKDE, etc.
Zhixun Li
is currently a Ph.D. student in the Department of Systems Engineering and Engineering Management at
the Chinese University of Hong Kong, supervised by Prof. Jeffrey Xu Yu. He received the B.Eng degree
in Computer Science from Beijing Institute of Technology. His research interests mainly focus on deep graph learning and
trustworthy AI. He has published papers at top international conferences, such as NeurIPS, SIGKDD, ICDM, and IJCAI. He
has also reviewed papers in many top-tier conferences and journals, like SIGKDD, ICDM, ICDE, etc.
Hong Cheng is a Professor in the Department of Systems Engineering and Engineering Management,
The Chinese University of Hong Kong. She received the Ph.D. degree from the University of Illinois at
Urbana-Champaign in 2008. Her research interests include data mining, database systems, and machine
learning. She received research paper awards at SIGKDD'23, ICDE'07, SIGKDD'06, and SIGKDD'05. She
received the 2010 Vice-Chancellor's Exemplary Teaching Award at The Chinese University of Hong Kong.
Jeffrey Xu Yu received the BE, ME, and PhD degrees in computer science from the University
of Tsukuba, Japan, in 1985, 1987, and 1990, respectively. He has held teaching positions with the
Institute of Information Sciences and Electronics, University of Tsukuba, and with the Department of
Computer Science, Australian National University, Australia. Currently, he is a professor at the
Department of Systems Engineering and Engineering Management, Chinese University of Hong Kong, Hong
Kong. His current research interests include graph database, graph mining, keyword search in relational
databases, and social network analysis.
@article{li2023survey,
title={A survey of graph meets large language model: Progress and future directions},
author={Li, Yuhan and Li, Zhixun and Wang, Peisong and Li, Jia and Sun, Xiangguo and Cheng, Hong and Yu, Jeffrey Xu},
journal={arXiv preprint arXiv:2311.12399},
year={2023}
}
@article{sun2023graph,
title={Graph prompt learning: A comprehensive survey and beyond},
author={Sun, Xiangguo and Zhang, Jiawen and Wu, Xixi and Cheng, Hong and Xiong, Yun and Li, Jia},
journal={arXiv preprint arXiv:2311.16534},
year={2023}
}
@article{chen2024graphwiz,
title={GraphWiz: An Instruction-Following Language Model for Graph Problems},
author={Chen, Nuo and Li, Yuhan and Tang, Jianheng and Li, Jia},
journal={arXiv preprint arXiv:2402.16029},
year={2024}
}
@article{li2024zerog,
title={ZeroG: Investigating Cross-dataset Zero-shot Transferability in Graphs},
author={Li, Yuhan and Wang, Peisong and Li, Zhixun and Yu, Jeffrey Xu and Li, Jia},
journal={arXiv preprint arXiv:2402.11235},
year={2024}
}
@article{zhao2024all,
title={All in one and one for all: A simple yet effective method towards cross-domain graph pretraining},
author={Zhao, Haihong and Chen, Aochuan and Sun, Xiangguo and Cheng, Hong and Li, Jia},
journal={arXiv preprint arXiv:2402.09834},
year={2024}
}
