Block Modeling-Guided Graph Convolutional Neural Networks


  • Dongxiao He Tianjin University
  • Chundong Liang Tianjin University
  • Huixin Liu Tianjin University
  • Mingxiang Wen Tianjin University
  • Pengfei Jiao Hangzhou Dianzi University
  • Zhiyong Feng Tianjin University



Data Mining & Knowledge Management (DMKM), Machine Learning (ML)


Graph Convolutional Network (GCN) has shown remarkable potential of exploring graph representation. However, the GCN aggregating mechanism fails to generalize to networks with heterophily where most nodes have neighbors from different classes, which commonly exists in real-world networks. In order to make the propagation and aggregation mechanism of GCN suitable for both homophily and heterophily (or even their mixture), we introduce block modelling into the framework of GCN so that it can realize “block-guided classified aggregation”, and automatically learn the corresponding aggregation rules for neighbors of different classes. By incorporating block modelling into the aggregation process, GCN is able to automatically aggregate information from homophilic and heterophilic neighbors discriminately according to their homophily degree. We compared our algorithm with state-of-art methods which deal with the heterophily problem. Empirical results demonstrate the superiority of our new approach over existing methods in heterophilic datasets while maintaining a competitive performance in homophilic datasets.




How to Cite

He, D., Liang, C., Liu, H., Wen, M., Jiao, P., & Feng, Z. (2022). Block Modeling-Guided Graph Convolutional Neural Networks. Proceedings of the AAAI Conference on Artificial Intelligence, 36(4), 4022-4029.



AAAI Technical Track on Data Mining and Knowledge Management