Beyond Over-smoothing: Uncovering the Trainability Challenges in Deep Graph Neural Networks
Jie Peng, Runlin Lei, Zhewei Wei.In CIKM 2024. [Download paper]
Runlin Lei's Homepage
About Me
Welcome to My Homepage. I’m Runlin Lei (雷润林), a second-year Ph.D. student at Renmin University of China, advised by Prof. Zhewei Wei. Before my Ph.D. journey, I obtained my Bachelor’s degree from Shanghai University of Finance and Economics, advised by Prof. Hongsong Yuan and Prof. Hua Liu.
I like sleeping and 🐷. Both are good. This is my GitHub homepage. Feel free to explore and learn more about me and my projects.
Contact information
Email: runlin_lei@ruc.edu.cn.
WeChat: JustL1ttleBit
Research interests
My interest lies in machine learning on graphs. Now I am working on graph adversarial attack & defense and LLM4Graph.
Publications
In CIKM 2024. [Download paper]Learning-based Property Estimation with Polynomials
Jiajun Li, Runlin Lei, Sibo Wang, Bolin Ding, Zhewei Wei.
In SIGMOD 2024. [Download paper]PolyGCL: Graph Contrastive Learning via Learnable Spectral Polynomial Filters
Jingyu Chen, Runlin Lei, Zhewei Wei.
In ICLR 2024. [Download paper] [code]Evennet: Ignoring odd-hop neighbors improves robustness of graph neural networks
Runlin Lei, Zhen Wang, Yaliang Li, Bolin Ding, Zhewei Wei.
In NIPS 2022. [Download paper] [code]
Services
I serve(d) as a program committee member / reviewer for:
- 2025: ICLR, AAAI
- 2024: NeurIPS, ICML, ICLR, KDD, ACML
- 2023: NeurIPS, ICML