| |
Research Seminar by QIAO Hezhe | | | DATE : | 3 July 2026, Friday | | TIME : | 3:00pm to 3:40pm | | VENUE : | Meeting room 4.4, Level 4
School of Computing and Information Systems 1,
Singapore Management University,
80 Stamford Road,
Singapore 178902
Please register by 2 July 2026 |
| 
|
*There are 2 talks in this session, each talk is approximately 20 minutes.* | | About the Talk (s) | Talk #1: Normality Calibration in Semi-supervised Graph Anomaly Detection | Semi-supervised Graph anomaly detection (GAD), which assumes a subset of annotated normal nodes available during training, is among the most widely explored application settings. However, the normality learned by existing semi-supervised GAD methods is limited to the labeled normal nodes, often inclining to overfitting the given patterns. These can lead to high detection errors, such as high false positives. To overcome this limitation, we propose GraphNC , a graph normality calibration framework that leverages both labeled and unlabeled data to calibrate the normality from a teacher model (a pre-trained semi-supervised GAD model) jointly in anomaly score and node representation spaces. GraphNC includes two main components, anomaly score distribution alignment (ScoreDA) and perturbation-based normality regularization (NormReg). ScoreDA optimizes the anomaly scores of our model by aligning them with the score distribution yielded by the teacher model. NormReg is designed to regularize the graph normality in the representation space, making the representations of normal nodes more compact by minimizing a perturbation-guided consistency loss solely on the labeled nodes.
This is a Pre-Conference talk for Forty-Third International Conference on Machine Learning (ICML 2026). | | Talk #2: TimeRadar: A Domain-Rotatable Foundation Model for Time Series Anomaly Detection | Current time series foundation models (TSFMs) primarily focus on learning prevalent and regular patterns within a predefined time or frequency domain to enable supervised downstream tasks (e.g., forecasting). Consequently, they are often ineffective for inherently unsupervised downstream tasks-such as time series anomaly detection (TSAD), which aims to identify rare, irregular patterns. This limitation arises because such abnormal patterns can closely resemble the regular patterns when presented in the same time/frequency domain. To address this issue, we introduce TimeRadar, an innovative TSFM built in a fractional time-frequency domain to support generalist TSAD across diverse unseen datasets. Our key insight is that rotating a time series into a data-dependent fractional time-frequency representation can adaptively differentiate the normal and abnormal signals across different datasets.
This is a Pre-Conference talk for ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2026). |
| | | | | About the Speaker  | | QIAO Hezhe is a forth-year Ph.D. candidate in Computer Science at the School of Computing and Information Systems, Singapore Management University, under the supervision of Prof. Pang Guansong. Prior to that, he received his MS degree from the University of Chinese Academy Science, China. His research interests lie in using deep learning and machine learning to build trustworthy AI systems. His work focuses on developing reliable and generalizable AI systems for detecting, explaining, and responding to unexpected anomalies across diverse data modalities. He has published multiple first-author articles in refereed top-tier venues, including NeurIPS, ICML, KDD, IJCAI, and TKDE. His research has attracted 800+ citations and received multiple awards, e.g., SMU Dean List and President’s Award of the Chinese Academy of Sciences. He is also the main organizer and presenter of the IJCAI 2025 tutorial titled ‘Deep Learning for Graph Anomaly Detection’. and AAAI 2026 tutorial titled ‘Toward Foundation Models for Detecting Abnormal Activities on Graphs’. |
|
|
|
