Zonghan Wu Assistant Professor
Research Areas:Graph Neural Networks, Time Series, Large Language Models
Email:zhwu@sem.ecnu.edu.cn
Dr. Zonghan Wu is an Assistant Professor at Shanghai AI-Finance School, East China Normal University. He received his PhD in Computer Science from the University of Technology Sydney in 2022. His research interests include graph machine learning and large language models. His work has been cited over 20,000 times on Google Scholar and has advanced the development of graph neural networks in complex and dynamic environments. Two of his papers were recognized as among the most influential papers at KDD 2020 and IJCAI 2019. He was awarded the 2024 IEEE CIS TNNLS Outstanding Paper Award.
Recent Work
1.FinAR-Bench (https://arxiv.org/pdf/2506.07315): Proposed a benchmark dataset for large language models in financial statement analysis, providing a systematic evaluation of 14 large models on three core financial tasks.
2.Financial Hallucination Detector: Developed a system for identifying factual and computational errors in financial analysis reports. Exhibited at WAIC 2025, supporting the safe and reliable application of AI in the financial domain.
3.Awesome-AI-Agents-Live (https://github.com/SAIFS-AIHub/Awesome-AI-Agents-Live):
Supervised students in developing a lightweight AI Agent paper-reading platform covering 8,000+ papers in AI Agent–related research.
Recent Publications
1. Zonghan Wu, Shirui Pan, Fengwen Chen, Guodong Long, Chengqi Zhang, Philip S. Yu: A Comprehensive Survey on Graph Neural Networks. IEEE Trans. Neural Networks Learn. Syst. 32(1): 4-24 (2021)
2. Zonghan Wu, Shirui Pan, Guodong Long, Jing Jiang, Xiaojun Chang, Chengqi Zhang:Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks. KDD 2020: 753-763
3. Zonghan Wu, Shirui Pan, Guodong Long, Jing Jiang, Chengqi Zhang:Graph WaveNet for Deep Spatial-Temporal Graph Modeling. IJCAI 2019: 1907-1913
Education Background
PhD in Computer Science, University of Technology Sydney
Research Interests
Graph Machine Learning
Large Language Models
