Non-Local Graph Neural Networks. Academic Article uri icon


  • Modern graph neural networks (GNNs) learn node embeddings through multilayer local aggregation and achieve great success in applications on assortative graphs. However, tasks on disassortative graphs usually require non-local aggregation. In addition, we find that local aggregation is even harmful for some disassortative graphs. In this work, we propose a simple yet effective non-local aggregation framework with an efficient attention-guided sorting for GNNs. Based on it, we develop various non-local GNNs. We perform thorough experiments to analyze disassortative graph datasets and evaluate our non-local GNNs. Experimental results demonstrate that our non-local GNNs significantly outperform previous state-of-the-art methods on seven benchmark datasets of disassortative graphs, in terms of both model performance and efficiency.

published proceedings

  • IEEE Trans Pattern Anal Mach Intell

altmetric score

  • 1

author list (cited authors)

  • Liu, M., Wang, Z., & Ji, S.

citation count

  • 8

complete list of authors

  • Liu, Meng||Wang, Zhengyang||Ji, Shuiwang

publication date

  • December 2022