Jie Peng (彭杰) is presently a third-year Ph.D. student at the Gaoling School of Artificial Intelligence, Renmin University of China, under the supervision of Prof. Zhewei Wei. Prior to this, he received his B.E. degree in Software Engineering from the School of Software Engineering, University of Electronic Science and Technology of China, in June 2023.

🔥 News

2025.09: We are excited to introduce a new benchmark for Generative DyTAG Learning, GDGB.
2025.05: 🎉🎉 One paper has been accepted by KDD 2025. Many thanks to my co-authors!
2025.01: 🎉🎉 One paper has been accepted by ICLR 2025. Many thanks to my co-authors!
2024.07: 🎉🎉 One paper has been accepted by CIKM 2024. Many thanks to my co-authors!

📝 Publications

TIDFormer: Exploiting Temporal and Interactive Dynamics Makes A Great Dynamic Graph Transformer. [Paper]
Jie Peng, Zhewei Wei*, Yuhang Ye.
In Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining. (KDD 2025)
Beyond Over-smoothing: Uncovering the Trainability Challenges in Deep Graph Neural Networks. [Paper]
Jie Peng, Runlin Lei, Zhewei Wei*.
In Proceedings of the 33rd ACM International Conference on Information and Knowledge Management. (CIKM 2024)
GDGB: A Benchmark for Generative Dynamic Text-Attributed Graph Learning. [Paper]
Jie Peng, Jiarui Ji, Runlin Lei, Zhewei Wei*, Yongchao Liu, Chuntao Hong*.
arXiv. (Preprint)
Beyond Leakage and Complexity: Towards Realistic and Efficient Information Cascade Prediction. [Paper]
Jie Peng, Rui Wang, Qiang Wang, Zhewei Wei*, Bin Tong, Guan Wang.
arXiv. (Preprint)
TGB-Seq Benchmark: Challenging Temporal GNNs with Complex Sequential Dynamics. [Paper]
Lu Yi, Jie Peng, Yanping Zheng*, Fengran Mo, Zhewei Wei*, Yuhang Ye, Yue Zixuan, Zengfeng Huang.
In Proceedings of the 13th International Conference on Learning Representations. (ICLR 2025)