Kay’s Homepage

Bio

I am an Applied Scientist at Amazon GuardDuty and a Computer Science PhD candidate at University of Illinois Chicago, advised by Prof. Philip S. Yu. I received my bachelor degree from Beijing University of Posts and Telecommunications and Queen Mary University of London in 2021. I also completed multiple internships as a scientist and engineer at Amazon and Walmart. My research interests include Graph Mining, Anomaly Detection, and Generative Models. More information about me can be found in my Curriculum Vitae.

TGTOD: A Global Temporal Graph Transformer for Outlier Detection at Scale.
Kay Liu, Jiahao Ding, MohamadAli Torkamani, Philip S. Yu.
PAKDD. 2025.
[Paper][Code]
Data Augmentation for Supervised Graph Outlier Detection with Latent Diffusion Models.
Kay Liu, Hengrui Zhang, Ziqing Hu, Fangxin Wang, Philip S. Yu.
LoG. 2024.
[Paper][Code]
BOND: Benchmarking Unsupervised Outlier Node Detection on Static Attributed Graphs.
Kay Liu, Yingtong Dou, Yue Zhao et al.
NeurIPS. 2022.
[Paper][Code][Data][Slides]
PyGOD: A Python Library for Graph Outlier Detection.
Kay Liu, Yingtong Dou, Yue Zhao et al.
JMLR. 2024.
[Paper][Code]
Enhancing Fairness in Unsupervised Graph Anomaly Detection through Disentanglement.
Wenjing Chang, Kay Liu, Philip S. Yu, Jianjun Yu.
TMLR. 2025.
[Paper][Code]
Multitask Active Learning for Graph Anomaly Detection.
Wenjing Chang, Kay Liu, Kaize Ding, Philip S. Yu, Jianjun Yu.
arXiv preprint. 2024.
[Paper][Code]

Graph Neural Network based Fraud Detection: from Research to Application at Wells Fargo
Graph Neural Network based Anomaly Detection: from Research to Application at BUAA
Graph Neural Network based Anomaly Detection: from Research to Application at Novartis
Leveraging GNNs for Financial Fraud Detection: Practices and Challenges at KDD 2022