Tutorial Description

Graph anomaly detection (GAD), which aims to identify rare observations in graphs, has attracted rapidly increasing attention in recent years due to its significance in a wide range of high-impact application domains such as abusive review detection and malicious behavior detection in online shopping applications, web attack detection, and suspicious activity detection in online/offline financial services. A foundation model on GAD refers to a generalist model trained on specific graph data, enabling it to generalize effectively across different domains and tasks. In recent years, such models have attracted increasing attention due to their ability to provide strong zero-shot and few-shot performance without task-specific retraining. By learning domain-invariant and transferable representations across tasks, a GAD foundation model can be readily adapted to new anomaly detection scenarios, making it applicable to a wide range of use cases such as privacy-preserving anomaly detection, transferable cybersecurity and threat detection, and cross-platform anomaly detection in social network. 

In this tutorial, we aim to present a comprehensive tutorial of deep learning methods specifically designed for GAD and foundation models for detecting abnormal activities on graphs. Specifically, we will first elaborate on the key concepts and taxonomies in GAD. Then review popular state-of-the-art deep anomaly detection methods from various perspectives of methodology design on graph data, including GNN backbone design, proxy task design, and anomaly measure. Then we will then establish the connection between conventional methods and foundation models on GAD, highlighting how recent advancements build upon or differ from conventional approaches. Following this, we will provide a comprehensive overview of existing foundation models that have been proposed for detecting abnormal activities on graphs from cross-domain and cross-task, respectively. We will  discuss their underlying principles, design choices, and effectiveness across various settings. The future directions will be finally presented to help researchers gain a deep understanding of this area and promote more high-quality research and real-world applications in the future. 

Resources

The survey and GitHub repo for this tutorial can be obtained here  (PDF,  Project) .   

Course Description

The planned agenda of the tutorial is as follows:

[30 mins] Opening Section 

•  Introduction to DLGAD

•  Problem and Challenge of DLGAD

•  Application of DLGAD

[60 mins] Methodology Part I: GNN Backbone Design 

•  Discriminative GNN methods

•  Generative GNN methods

[30 mins] Methodology Part II: Proxy Task Design 

•  Graph Reconstruction

•  Graph Contrastive Learning  

•  Graph Representation Distillation

•  Adversarial Graph Learning

•  Score Prediction

[30 mins] Methodology Part III: Graph Anomaly Measures 

•  One-class Classification Measure

•  Community Adherence

•  Local Node Affinity-Based Anomaly Measure

•  Graph Isolation 

[30 mins] Conclusion Section

•  Summarization of the Advances in DLGAD

•  Future Research Opportunities for DLGAD

Tutorial Organizers and Speakers

Hezhe Qiao,  PhD 

Bio: Hezhe Qiao is a Ph.D. candidate at Singapore Management University. His research interests include graph representation learning, graph anomaly detection, and the combination of anomaly detection and large language models. He has published multiple articles in refereed top-tier venues, including NeurIPS, ICML, KDD, IJCAI, and TKDE. He has received several awards, such as the Mark Weiser Best Paper Award in PerCom (2024) and SMU Presidential Doctoral Fellowship Award (2024,2025), SMU Dean List (2025) and President’s Award of the Chinese Academy of Sciences (2022), First prize, Dean Scholarship of Chengdu Branch, Chinese Academy of Science (2021). He organized the IJCAI2025 tutorial titled "Deep learning for graph anomaly detection". He also served on the program committees of multiple top conferences and journals.

Dr. Hanghang Tong, Professor 

Bio: Hanghang Tong is currently a professor at Siebel School of Computing and Data Science at University of Illinois at Urbana-Champaign. Before that he was an associate professor at Arizona State University. He received his M.Sc. and Ph.D. degrees from Carnegie Mellon University in 2008 and 2009, both in Machine Learning. His research interest is in large scale data mining for graphs and multimedia. He has received several awards, including  IEEE ICDM Tao Li award (2019), SDM/IBM Early Career Data Mining Research award (2018), NSF CAREER award (2017), ICDM 10-Year Highest Impact Paper awards (2015 and 2022), and several best paper awards. He has published over 300 refereed articles. He was the Editor-in-Chief of ACM SIGKDD Explorations (2018-2022) and is an associate editor of ACM Computing Surveys. He is a distinguished member of ACM and a fellow of IEEE.

Dr. Bo An, Professor 

Bio: Bo An is a President's Chair Professor and Head of Division of Artificial Intelligence at the College of Computing and Data Science of the Nanyang Technological University (NTU). He is also Director for Centre of AI-for-X of NTU. He is the recipient of the 2010 IFAAMAS Victor Lesser Distinguished Dissertation Award, an Operational Excellence Award from the Commander, First Coast Guard District of the United States, the 2012 INFORMS Daniel H. Wagner Prize for Excellence in Operations Research Practice, 2018 Nanyang Research Award (Young Investigator), and 2022 Nanyang Research Award. His publications won the Best Innovative Application Paper award at AAMAS'12 and the Innovative Application Award at IAAI'16. He was invited to give Early Career Spotlight talk at IJCAI'17. He led the team HogRider which won the 2017 Microsoft Collaborative AI Challenge. He was named to IEEE Intelligent Systems' "AI's 10 to Watch" list for 2018. He is on the IJCAI Board of Trustees and will be Program Chair of IJCAI’27. He is Editor-in-Chief of IEEE Intelligent Systems. He is the Associate Editor of Artificial Intelligence Journal (AIJ), Journal of Autonomous Agents and Multi-agent Systems (JAAMAS), ACM Transactions on Intelligent Systems and Technology, and ACM Transactions on Autonomous and Adaptive Systems and a member of the editorial board of Journal of Artificial Intelligence Research (JAIR). He was elected to the board of directors of IFAAMAS, senior member of AAAI, and Distinguished member of ACM.

Dr. Irwin King, Professor 

Bio: Irwin King is a world renowned scholar in machine intelligence, currently Professor and immediate Past-chair of Computer Science Engineering at The Chinese University of Hong Kong. With a broad range of research interests covering areas such as trustworthy AI, machine learning, social computing, AI, and data mining, Professor King is a Fellow of prestigious societies and associations, including the ACM, IEEE, INNS, AAIA, and HKIE. Over the years, he has played many leadership roles in various top conferences and societies, such as serving as the President of the International Neural Network Society, General Co-chair of conferences such as WebConf 2020, ICONIP 2020, ACML 2015, RecSys 2013, and WSDM 2011.

Dr. Charu Aggarwal, Professor 

Bio: Charu Aggarwal is a Distinguished Research Staff Member (DRSM) at the IBM T. J. Watson Research Center in Yorktown Heights, New York. He has worked extensively in the field of data mining, with particular interests in data streams, privacy, uncertain data and social network analysis. He has authored 10 books, over 400 papers in refereed venues, and has applied for or been granted over 80 patents. His h-index is 136.  He is a recipient of an IBM Corporate Award (2003) for his work on bio-terrorist threat detection in data streams, a recipient of the IBM Outstanding Innovation Award (2008) for his scientific contributions to privacy technology, and a recipient of two IBM Outstanding Technical Achievement Awards (2008) for his scientific contributions to high-dimensional and data stream analytics. He has received two best paper awards and an EDBT Test-of-Time Award (2014). He is a recipient of the IEEE ICDM Research Contributions Award (2015) and the ACM SIGKDD Innovation Award (2019), which are the two most prestigious awards for influential research in data mining.

Dr. Guansong Pang, Assistant Professor 

Bio: Guansong Pang is a tenure-track Assistant Professor of Computer Science at the School of Computing and Information Systems, Singapore Management University (SMU), Singapore. He obtained his PhD degree at University of Technology Sydney (UTS). His research interest generally lies in machine learning and their applications, with a particular focus on detecting abnormal or unknown instances from different types of data. He has published more than 40 papers in refereed conferences and journals, such as CVPR, ICCV, ECCV, ACM MM, KDD, AAAI, and IJCAI. He is one of the main speakers of KDD’21 and WSDM’21 tutorials on deep anomaly detection, and one of the main organizers of ANDEA and AI4AN workshop series on anomaly and novelty detection at IJCAI and KDD. He also served as a (lead) guest editor of IEEE TNNLS on “deep learning for anomaly detection”. He was named on the prestigious 2020 UTS Chancellor's Award List and the list of The World's Top 2% Scientists (single recent year) released by Stanford University in 2022-2024.

Contact

Hezhe Qiao hezheqiao.2022@phdcs.smu.edu.sg and Dr. Guansong Pang, gspang@smu.edu.sg