Yifei Sun

I am a CS Ph.D. student at Zhejiang University, fortunately advised by Prof. Yang Yang. Previously, I visit National University of Singapore (working with Prof. Bingsheng He, Prof. Bryan Hooi and Prof. Zemin Liu).

My current research interests lie primarily in the area of Machine Learning and Data Mining on Graphs, including but not limited to graph neural networks, graph pre-training, and real-world applications on graphs. Moreover, in this era of LLMs, I hope to contribute my efforts to the Graph foundation model and Graph LLMs.

⭐️ The main goal of my research is to build generalizable graph models that can be trained on rich and complex graph data, enhancing its capability across various downstream data and tasks.

Ongoing Work

  • [🌏Generalization at the Graph Principle Level] Towards Graph Foundation Model across Domains.
  • [💡Generalization at the Graph Task Level] Graph LLM for Zero-Shot Multi-Label Node Classification.
  • [💡Generalization at the Graph Task Level] Tackling Multi-label Node Classification. (Under Review)

If interested, please drop me a message by email.


Selected Publications (Full version see Google Scholar)

Narrow the Gap between Graph Pre-training and Fine-tuning

[🎈Generalization at the Graph Data Level]

  • Yifei Sun, Qi Zhu, Yang Yang, Chunping Wang, Tianyu Fan, Jiajun Zhu, Lei Chen. Fine-tuning Graph Neural Networks by Preserving Graph Generative Patterns. In Proceedings of the 36th AAAI Conference on Artificial Intelligence (AAAI’24), 2024. Paper

Break the limitation of GNNs on graph data homophily

[🎈Generalization at the Graph Data Level]

  • Yifei Sun, Haoran Deng, Yang Yang, Chunping Wang, Jiarong Xu, Renhong Huang, Linfeng Cao, Yang Wang, and Lei Chen. Beyond Homophily: Structure-aware Path Aggregation Graph Neural Network. In Proceedings of the 31st International Joint Conference on Artificial Intelligence (IJCAI’22), 2022. Paper

Academic Activities