Pre-train and Learn: Preserve Global Information for Graph Neural Networks
This addresses limitations in graph neural networks for researchers and practitioners working with both plain and attributed graphs, offering incremental improvements.
The paper tackles the challenge of GNNs utilizing distant node information and handling plain graphs by proposing G-GNNs, which use unsupervised pre-training to capture global features and a parallel framework, achieving new benchmark records of 84.31% on Cora and 80.95% on Pubmed.
Graph neural networks (GNNs) have shown great power in learning on attributed graphs. However, it is still a challenge for GNNs to utilize information faraway from the source node. Moreover, general GNNs require graph attributes as input, so they cannot be appled to plain graphs. In the paper, we propose new models named G-GNNs (Global information for GNNs) to address the above limitations. First, the global structure and attribute features for each node are obtained via unsupervised pre-training, which preserve the global information associated to the node. Then, using the global features and the raw network attributes, we propose a parallel framework of GNNs to learn different aspects from these features. The proposed learning methods can be applied to both plain graphs and attributed graphs. Extensive experiments have shown that G-GNNs can outperform other state-of-the-art models on three standard evaluation graphs. Specially, our methods establish new benchmark records on Cora (84.31\%) and Pubmed (80.95\%) when learning on attributed graphs.