Interview with Thi Kieu Khanh Ho: Time-series anomaly detection

Summary

In the latest interview with AAAI/SIGAI Doctoral Consortium participants, Thi Kieu Khanh Ho, a PhD student at McGill University and Mila – Québec AI Institute, discusses her research on time-series anomaly detection. Her work focuses on teaching AI systems to detect unusual events in complex real-world data streams without relying on large amounts of labeled examples, which are often scarce, noisy, or contaminated. She has developed EEG-CGS, a contrastive and generative self-supervised framework that detects anomalous channels in EEG recordings for seizure detection, performing well without any labeled seizures during training. She also created TSAD-C, a graph- and diffusion-based framework for multivariate time-series anomaly detection that addresses the challenge of contaminated training data. Additionally, she has contributed two surveys, one on self-supervised learning for anomaly detection and one on graph-based time-series anomaly detection.