Non-Local Graph Neural Networks
Non-Local Graph Neural Networks
复制标题
DOI：
10.1109/tpami.2021.3134200
复制
发表时间：
2022-12-01
影响因子：
23.6
通讯作者：
Ji, Shuiwang
中科院分区：
文献类型：
--
作者：
Liu, Meng;Wang, Zhengyang;Ji, Shuiwang
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.
