School of Information and Software Engineering
Intelligent Computing and Data Mining Lab
ICDM Lab works at the intersection of data mining and artificial intelligence. We build trustworthy, explainable, and generative methods for graph, spatio-temporal, and multimodal data — and increasingly build on foundation models — to turn large-scale, real-world data into reliable knowledge and deployable systems.
Research
Trustworthy and Explainable AI
Can a model's explanations be inspected and relied upon when the stakes are high?
Learn more →Graph Learning
How do we detect anomalies and make reliable predictions on relational data?
Learn more →Social Computing
How does multimodal content spread, and how can harmful content be identified?
Learn more →Foundation Models and Agents
How do we adapt large pretrained models to new domains, and what can agents built on them do reliably?
Learn more →AI for Industry and Healthcare
What changes when these methods meet scarce, irregular, or sensitive real-world data?
Learn more →Selected publications
Harmonic Canvas: Inversion-Free Editing for Visually-Guided Music Style Transfer
Yue Lei, Siqi Yang, Ting Zhong, Fan Zhou
Disentangling Multi-View Scanning in Mamba for Network Traffic Anomaly Detection
Xinglin Lian, Chengtai Cao, Ting Zhong, Fan Zhou
From Shallow Humor to Metaphor: Towards Label-Free Harmful Meme Detection via LMM Agent Self-Improvement
Jian Lang, Rongpei Hong, Ting Zhong, Leiting Chen, Qiang Gao, Fan Zhou
Consensus-Driven Distillation for Trustworthy Explanations in Self-Interpretable GNNs
Wenxin Tai, Fan Zhou, Steve Azzolin, Goce Trajcevski, Ting Zhong, Kunpeng Zhang
Latest news
- Wenxin Tai and Chengtai Cao join the lab as postdocs
- Wenxin Tai passes his doctoral dissertation defense
- Wenxin Tai nominated for the UESTC Most Outstanding Graduate Students Award
