Non-Local Graph Neural Networks
This addresses a key limitation in GNNs for tasks on disassortative graphs, which is important for applications in domains like social networks or biology where such graphs are common.
The paper tackled the problem of graph neural networks (GNNs) underperforming on disassortative graphs due to harmful local aggregation, and proposed a non-local aggregation framework that significantly outperforms previous state-of-the-art methods on seven benchmark datasets.
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.