Hi, my name is Zitong Shi (Chinese: 史梓桐), a 4-year undergraduate student at Wuhan University. I have closely collaborated with Prof. Mang Ye, Prof. Carl J Yang, Guancheng Wan, and Wenke Huang. I am seeking PhD opportunities for Fall 2026.🔥🔥

🔍 Research

My academic exploration focuses on the deep analysis and dynamic relationship modeling of graph-structured data. Currently, my research is focused on:

  • Large Language Models 🧠
  • Multi-agent systems 🤖
  • Graph learning 📍

🔥 News

  • 2025.05: 🎉🎉🎉One paper was accepted by ICML 2025.
  • 2025.01: 🎉🎉🎉One paper was accepted by ICLR 2025.

📃 Publications

† Equal Contribution

Energy-based Backdoor Defense Against Federated Graph Learning
Zitong Shi†, Guancheng Wan†, Wenke Huang, Guibin Zhang, Dacheng Tao, Mang Ye
Oral Presentation (1.8%) in International Conference on Learning Representations (ICLR), 2025
EAGLES: Towards Effective, Efficient, and Economical Federated Graph Learning via Unified Sparsification
Zitong Shi†, Guancheng Wan†, Wenke Huang, Guibin Zhang, He Li, Carl Yang, Mang Ye
in International Conference on Machine Learning (ICML), 2025

📝 Manuscripts

Don’t Forget the Enjoin: FocalLoRA for Instruction Hierarchical Alignment in Large Language Models
under review
Privacy-Enhancing Paradigms within Federated Multi-Agent Systems
under review
Multi-order Orchestrated Curriculum Distillation for Model-Heterogeneous Federated Graph Learning
under review
Towards Robust Text-Attributed Federated Graph Learning: Multimodal Threats and Defense
under review

🎡 Service

Conference Committee Member

  • Reviewer for ICML’2025

Journal Reviewer

  • Reviewer for IEEE Transactions on Neural Networks and Learning Systems (TNNLS)
  • Reviewer for IEEE Transactions on Image Processing (TIP)


📖 Education

2022.09 - Now
Undergraduate, School of Computer Science, Wuhan University
Wuhan University Logo