Deep Graph Structural Infomax


  • Wenting Zhao Nanjing University of Science and Technology, Nanjing, China.
  • Gongping Xu Nanjing University of Science and Technology, Nanjing, China.
  • Zhen Cui Nanjing University of Science and Technology, Nanjing, China.
  • Siqiang Luo Nanyang Technological University, Singapore.
  • Cheng Long Nanyang Technological University, Singapore.
  • Tong Zhang Nanjing University of Science and Technology, Nanjing, China.



DMKM: Graph Mining, Social Network Analysis & Community Mining, ML: Classification and Regression, ML: Graph-based Machine Learning


In the scene of self-supervised graph learning, Mutual Information (MI) was recently introduced for graph encoding to generate robust node embeddings. A successful representative is Deep Graph Infomax (DGI), which essentially operates on the space of node features but ignores topological structures, and just considers global graph summary. In this paper, we present an effective model called Deep Graph Structural Infomax (DGSI) to learn node representation. We explore to derive the structural mutual information from the perspective of Information Bottleneck (IB), which defines a trade-off between the sufficiency and minimality of representation on the condition of the topological structure preservation. Intuitively, the derived constraints formally maximize the structural mutual information both edge-wise and local neighborhood-wise. Besides, we develop a general framework that incorporates the global representational mutual information, local representational mutual information, and sufficient structural information into the node representation. Essentially, our DGSI extends DGI and could capture more fine-grained semantic information as well as beneficial structural information in a self-supervised manner, thereby improving node representation and further boosting the learning performance. Extensive experiments on different types of datasets demonstrate the effectiveness and superiority of the proposed method.




How to Cite

Zhao, W., Xu, G., Cui, Z., Luo, S., Long, C., & Zhang, T. (2023). Deep Graph Structural Infomax. Proceedings of the AAAI Conference on Artificial Intelligence, 37(4), 4920-4928.



AAAI Technical Track on Data Mining and Knowledge Management