I am now a Ph.D. student of the School of Intelligence Science and Technology of Peking University, advised by Prof. Muhan Zhang. Our group’s github page is GraphPKU.

My recent work is centered around graph neural network (GNN), particularly on GNN’s expressivity. If you’re also interested in related fields, welcome to contact me!

📖 Educations

• 2022.09 -, Ph.D. student, School of Intelligence Science and Technology, Peking University
• 2018.09 - 2022.07, B.E., College of Chemistry and Molecular Engineering, Peking University

📝 Publications

• Xiyuan Wang, Muhan Zhang, Neural Common Neighbor with Completion for Link Prediction, ICLR, 2024.
• Xiyuan Wang, Muhan Zhang, GLASS: GNN with labeling tricks for subgraph representation learning, ICLR 2022.
• Xiyuan Wang, Muhan Zhang, How powerful are spectral graph neural networks, ICML, 2022.
• Xiyuan Wang, Muhan Zhang, Graph neural network with local frame for molecular potential energy surface, Learning on Graphs Conference, 2023.
• Zian Li, Xiyuan Wang, Shijia Kang, Muhan Zhang, On the Completeness of Invariant Geometric Deep Learning Models, arXiv preprint, 2024.
• Zian Li, Xiyuan Wang, Yinan Huang, Muhan Zhang, Is Distance Matrix Enough for Geometric Deep Learning?, NeurIPS, 2023.
• Cai Zhou, Xiyuan Wang, Muhan Zhang, Facilitating Graph Neural Networks with Random Walk on Simplicial Complexes, NeurIPS, 2023.
• Cai Zhou, Xiyuan Wang, Muhan Zhang, From Relational Pooling to Subgraph GNNs: A Universal Framework for More Expressive Graph Neural Networks, ICML, 2023.