Zhong Li - Research

Research Summary

Research Interests: I am interested in the field of Data Mining and Machine Learning. More specifically, I work on explainable and generalizable anomaly detection, with a focus on but not limited to complex data such as event sequence and graph-structured data.

Research Keywords:

Methodologies-Oriented: Unsupervised Machine Learning; Anomaly Detection; Transfer Learning; XAI; Graph Neural Networks
Applications-Oriented: Log Analysis; Predictive Maintenance; Digital Twin; AI for Manufacturing

Collaborations: I am currently working on Graph Level tasks such as Graph Level Anomaly Detection, Graph Level Clustering using GNNs. I am actively looking for collaborations if you are also interested in these amazing things (Please drop me an email).

Publications

Published:

Zhong Li, Matteo Quartagno, Stefan Böhringer, and Nan van Geloven. (2022), Choosing and changing the analysis scale in non-inferiority trials with a binary outcome, Clinical Trials.19(1): 14-21.
Zhong Li & Matthijs van Leeuwen (2022), Feature Selection for Fault Detection and Prediction based on Log Analysis. SIGKDD Explorations Newsletter. 24, 2 (December 2022), 96–104.
Zhong Li, Yuxuan Zhu & Matthijs van Leeuwen (2023), A Survey on Explainable Anomaly Detection. ACM Trans. Knowl. Discov. Data (TKDD) (July 2023)
Zhong Li & Matthijs van Leeuwen (2023), Explainable Contextual Anomaly Detection using Quantile Regression Forests. Data Mining and Knowledge Discovery (DAMI). (August 2023)
Zhong Li, Sheng Liang, Jiayang Shi, Matthijs van Leeuwen (2024), Cross Domain Graph Level Anomaly Detection. IEEE Transactions on Knowledge and Data Engineering (TKDE).

Under Review:

Zhong Li, Jiayang Shi, Matthijs van Leeuwen (2023), Graph Neural Networks based Log Anomaly Detection and Explanation. (Accepted by ICSE'24 poster track, and the full version is under review for EAAI journal.)
Zhong Li, Yuhang Wang, Matthijs van Leeuwen (2024), Automated Self-Supervised Learning on Graphs (Submitted to DAMI)
Zhong Li, Simon Geisler, Yuhang Wang, Stephan Günnemann, Matthijs van Leeuwen (2024), Explainable Graph Neural Networks Under Fire (Submitted to TKDE)
Yuhang Wang*, Zhong Li*, Shujian Yu, Matthijs van Leeuwen (2024), Evaluating Node Embedding Quality without Relying on Labels. (Submitted to a ML conference)

In Preparation:

[Methodology] Automated Feature Selection for Anomaly Detection, with Yuhang Wang et al. (Writing and aiming for TKDE)
[Methodology] Robustness of Graph Anomaly Detection, with Stephan Günnemann, and Matthijs van Leeuwen.
[Methodology] Understanding Graph Self-Supervised Learning with Information Theory, with Matthijs van Leeuwen.
[Application] Data-driven inkjet jet failure detection and classification using piezo self-sensing, with Yuxuan Zhu & Matthijs van Leeuwen.
[Application] Combining sensor monitoring data and system logs for fault detection and explanation, with Matthijs van Leeuwen.
Maybe the next great idea is with you...🤝

Professional Services

Reviewer for KDD conference, ICLR conference
Invited Reviewer for the following journals:
- IEEE Transactions on Knowledge and Data Engineering (TKDE)
- Data Mining and Knowledge Discovery (DMKD or DAMI)
- IEEE Internet of Things Journal
- AI Communications

Page updated

Google Sites

Report abuse