About Me
👋 I'm Runlin Lei (雷润林), a fourth-year Ph.D. student at Renmin University of China. I'm a member of the ALGO Lab, advised by Prof. Zhewei Wei. My research interests primarily focus on LLM & Graph, Trustworthy Graph Learning.
🎓 Before embarking on my Ph.D. journey, I earned my Bachelor's degree from Shanghai University of Finance and Economics, where I was advised by Prof. Hongsong Yuan and Prof. Hua Liu.
📧 Feel free to reach out to me via email: runlin_lei@ruc.edu.cn.
Publications
Graph & LLMs
-
GDGB: A Benchmark for Generative Dynamic Text-Attributed Graph Learning
Jie Peng, Jiarui Ji, Runlin Lei, Zhewei Wei, Yongchao Liu, Chuntao Hong.
Preprint [Download paper] [code] -
Exploring the Potential of Large Language Models as Predictors in Dynamic Text-Attributed Graphs
Runlin Lei, Jiarui Ji, Haipeng Ding, Lu Yi, Zhewei Wei, Yongchao Liu, Chuntao Hong.
Preprint [Download paper] -
Leveraging LLM-Based Agents for Social Science Research: Insights from Citation Network Simulations
Jiarui Ji, Runlin Lei, Xuchen Pan, Zhewei Wei, Hao Sun, Yankai Lin, Xu Chen, Yongzheng Yang, Yaliang Li, Bolin Ding, Ji-Rong Wen.
In HSSCOMMS 2025. [Download paper] -
LLM-Based Multi-Agent Systems are Scalable Graph Generative Models
Jiarui Ji, Runlin Lei, Jialing Bi, Zhewei Wei, Yankai Lin, Xuchen Pan, Yaliang Li, Bolin Ding.
In ACL (Findings) 2024. [Download paper] [code] -
Robustness in Text-Attributed Graph Learning: Insights, Trade-offs, and New Defenses
Runlin Lei, Lu Yi, Mingguo He, Pengyu Qiu, Zhewei Wei, Yongchao Liu, Chuntao Hong.
Preprint [Download paper] -
Scalable and Accurate Graph Reasoning with LLM-based Multi-Agents
Yuwei Hu, Runlin Lei, Xinyi Huang, Zhewei Wei, Yongchao Liu.
Preprint [Download paper]
Trustworthy Graph Learning
-
Restricted Black-Box Attacks on Graphs Beyond Homophily
Runlin Lei, Haipeng Ding, Zhewei Wei.
In TKDE 2025. -
Intruding with Words: Towards Understanding Graph Injection Attacks at the Text Level
Runlin Lei, Yuwei Hu, Yuchen Ren, Zhewei Wei.
In NeurIPS 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 NeurIPS 2022. [Download paper] [code]
General Graph Learning
-
Future Link Prediction Without Memory or Aggregation
Lu Yi, Runlin Lei, Fengran Mo, Yanping Zheng, Zhewei Wei, Yuhang Ye.
In NeurIPS 2025. [Download paper] -
Beyond Over-smoothing: Uncovering the Trainability Challenges in Deep Graph Neural Networks
Jie Peng, Runlin Lei, Zhewei Wei.
In CIKM 2024. [Download paper] -
PolyGCL: Graph Contrastive Learning via Learnable Spectral Polynomial Filters
Jingyu Chen, Runlin Lei, Zhewei Wei.
In ICLR 2024. [Download paper] [code]
Others
-
Learning-based Property Estimation with Polynomials
Jiajun Li, Runlin Lei, Sibo Wang, Bolin Ding, Zhewei Wei.
In SIGMOD 2024. [Download paper]
Talks
- 2023-10: Gave a talk about Evennet: Ignoring odd-hop neighbors improves robustness of graph neural networks to the Complex Networks Analysis discussion group. Talk Link
- 2022-10: Gave a talk about Evennet: Ignoring odd-hop neighbors improves robustness of graph neural networks to AITIMES. Talk Link
Honors & Scholarships
- 2024, 2023: Academic Excellence Scholarship, Academic Scholarship
- 2022: Shanghai Excellent Graduate, School Excellent Graduate
- 2021: China Merchants Bank Scholarship, American Undergraduate Mathematical Modeling Competition M Award, National Mathematical Modeling Competition National Second Prize
- 2020: People's Scholarship First Prize
- 2019: National Scholarship
Services
I serve(d) as a program committee member / reviewer for:
- 2025: ICLR, AAAI, TPAMI
- 2024: NeurIPS, ICML, ICLR, KDD, ACML
- 2023: NeurIPS, ICML