About

Mingguo He is presently a fourth-year Ph.D. student at the Gaoling School of Artificial Intelligence, Renming University of China, under the guidance of Prof. Zhewei Wei. Prior to this, he attained his B.E. degree in Software Engineering from the School of Computer Science, Central South University in June 2020.

Research Interests

• Spectral Graph Neural Networks
• Graph Transformer
• Heterogeneous Graph Neural Networks
• Directed Graph Neural Networks.

Publication

• Spectral Heterogeneous Graph Convolutions via Positive Noncommutative Polynomials. [Paper][Code]
  Mingguo He,Zhewei Wei, Shikun Feng, Zhengjie Huang, Weibin Li, Yu Sun, Dianhai Yu.
  In Proceedings of the ACM Web Conference 2024. (TheWebConf 2024, Oral Presentation)
  

• Convolutional Neural Networks on Graphs with Chebyshev Approximation, Revisited. [Paper][Code]
  Mingguo He, Zhewei Wei, Ji-Rong Wen.
  In the 36th Conference on Neural Information Processing Systems. (NeurIPS 2022, Oral Presentation)
  

• BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximation. [Paper][Code]
  Mingguo He, Zhewei Wei, Zengfeng Huang, Hongteng Xu.
  The 35th Conference on Neural Information Processing Systems. (NeurIPS 2021)
  

• Approximate Graph Propagation. [Paper][Code]
  Hanzhi Wang, Mingguo He, Zhewei Wei, Sibo Wang, Ye Yuan, Xiaoyong Du, Ji-Rong Wen.
  Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. (KDD 2021)
  

Preprint

• PolyFormer: Scalable Graph Transformer via Polynomial Attention. [Paper]
  Jiahong Ma, Mingguo He, Zhewei Wei.