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.
翻译:光电图网络(GNNs)在学习配给图上表现出巨大的力量。 然而,对于GNNs来说,利用远离源节点的信息仍然是一项挑战。 此外,一般GNNs需要图形属性作为输入,因此不能以苹果形式显示为普通图形。在论文中,我们提出了名为G-GNNs(GNNs的全球信息)的新模型,以解决上述局限性。首先,每个节点的全球结构和属性是通过未经监督的预培训获得的,这保留了与节点相关的全球信息。然后,利用全球特征和原始网络属性,我们提出了一个GNNNs的平行框架,以学习这些特征的不同方面。拟议的学习方法可以适用于简单的图表和可归属的图表。广泛的实验表明,G-GNNNs可以在三个标准评价图表上超越其他最先进的模型。特别是,我们的方法在学习配给的图表时,在Cora(84.31 ⁇ )和Pubmed(80.95 ⁇ )上建立了新的基准记录。