Bryan HOOI Kuen-Yew
Assistant Professor- PhD in Machine Learning, Carneige Mellon University, 2019
- MSc in Computer Science and BSc in Mathematics, Stanford University, 2014
Bryan HOOI is an assistant professor in the Computer Science Department, School of Computing at the National University of Singapore. He has obtained his PhD degree in Machine Learning from Carnegie Mellon University, USA in 2019, his Master of Science degree in Computer Science and Bachelor with Honours degree in Mathematics from Stanford University, USA in 2014. His research interests include machine learning, graph mining, anomaly detection, spatiotemporal data, and biomedical applications of AI.
RESEARCH AREAS
RESEARCH INTERESTS
Machine Learning
Graph Algorithms
Anomaly Detection
Spatiotemporal Data
Biomedical Applications of AI
RESEARCH PROJECTS
Enhancing Reliability and Relational Understanding of Visual Language Models
This research aims to address the limitations of Visual Language Models (VLMs), including hallucinations and poor relational understanding. The project proposes benchmarks to evaluate and understand these issues, and develops improved decoding approaches to detect and prevent hallucinations during text generation, enhancing VLM reliability and accuracy.
RESEARCH GROUPS
TEACHING INNOVATIONS
SELECTED PUBLICATIONS
- Minji Yoon,Bryan Hooi, Kijung Shin and Christos Faloutsos.Fast and Accurate Anomaly Detection in Dynamic Graphs with a Two-Pronged Approach,ACM SIGKDD Conference on Knowledge Discovery and Data Mining KDD2019.
- Bin Zhou, Shenghua Liu,Bryan Hooi, Xueqi Cheng, and Jing Ye.BeatGAN: Anomalous Rhythm Detection using Adversarially Generated Time Series,International Joint Conference on Artificial Intellince IJCAI2019.
- Bryan Hooi, Dhivya Eswaran, Hyun Ah Song, Amritanshu Pandey, Marko Jereminov, Larry Pileggi, and Christos FaloutsosGridWatch: Sensor Placement and Anomaly Detection in the Electrical Grid.European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases ECML-PKDD2018.Runner-up Best Student Data Mining Paper Award
- Bryan Hooi, Hyun Ah Song, Alex Beutel, Neil Shah, Kijung Shin, and Christos Faloutsos.FRAUDAR: Bounding Graph Fraud in the Face of Camouflage.ACM SIGKDD Conference on Knowledge Discovery and Data Mining KDD2016.KDD Best Paper Award Research Track
AWARDS & HONOURS
ECML-PKDD 2018 Runner-Up Best Student Data Mining Paper Award
KDD 2016 Best Paper Award (Research Track)
COURSES TAUGHT
CS4225
Big Data Systems for Data Science
CS5425
Big Data Systems for Data Science