Foundation models have revolutionized machine learning by enabling general-purpose reasoning across diverse tasks and domains. These models, pretrained on large-scale data, demonstrate strong adaptability with minimal task-specific supervision, leading to breakthroughs in natural language processing and computer vision. Inspired by this paradigm, Graph Foundation Models (GFMs) have emerged to extend the benefits of foundation models to graph-structured data, which is pretrained on massive graphs and can be fast adapted to different downstream tasks. In this tutorial, we will focus on the state-of-the-art techniques of graph foundation models, in particular, a series of graph model-based methods, language model-based methods, and their real-world applications. The objectives of this tutorial are to: (1) formally categorize the challenges in designing graph foundation models; (2) comprehensively review the existing and recent advances of graph foundation models; (3) extend the graph foundation models in real-world problems; and (4) elucidate open questions and future research directions. This tutorial introduces major topics within foundation models and offers a guide to a new frontier of graph learning.

Zehong Wang is currently a Ph.D. candidate at University of Notre Dame. His research interests are broadly in machine learning and data mining, with a particular focus on foundation models. His work has appeared at top conferences such as NeurIPS, ICML, KDD, ACL, NAACL, IJCAI, and WSDM. 

Chuxu Zhang is an Associate Professor of Computer Science and Engineering at the University of Connecticut, with research interests at the intersection of artificial intelligence, graph machine learning, large language models, and their societal applications. His research has led to over 100 papers in major AI venues such as ICML, NeurIPS, ICLR, KDD, and WWW. He is the recipient of the NSF CAREER Award (2024) and several best paper (candidate) awards including CIKM 2021 and WWW 2022. 

Jundong Li is an Assistant Professor of ECE and CS at the University of Virginia. His research interests primarily lie in data mining and machine learning, with a particular emphasis on graph mining, causal inference, and algorithmic fairness. He has published over 150 papers in high-impact venues, such as KDD, WWW, and NeurIPS, accumulating more than 10,000 citations. His work has earned him several prestigious awards, including the SIGKDD 2024 Rising Star Award, the SIGKDD 2022 Best Research Paper Award, the NSF CAREER Award, the JP Morgan Chase Faculty Research Award, and the Cisco Faculty Research Award. 

Nitesh V. Chawla is the Frank M. Freimann Professor of Computer Science and Engineering at the University of Notre Dame. His research focuses on artificial intelligence, data science, and network science. He is the recipient of National Academy of Engineers New Faculty Fellowship; the 2015 IEEE CIS Outstanding Early Career Award; the IBM Watson Faculty Award; the IBM Big Data and Analytics Faculty Award; the National Academy of Engineering New Faculty Fellowship; He is a fellow of ACM, IEEE, AAAS, AAAI. 

Yanfang Ye is the Galassi Family Collegiate Professor in Computer Science and Engineering at the University of Notre Dame. Her research areas mainly include artificial intelligence, machine learning, data mining, cybersecurity, and public health. Her research leads to over 150 publications in top-tier conferences and journals. She have received multiple awards from the NSF and DoJ/NIJ in support of our research, including NSF Career Award (2019). Also, she have received nine best paper awards, including WWW 2022, CIKM 2021, and SIGKDD 2017.