Link prediction is one of the key problems for graph-structured data. With the advancement of graph neural networks, graph autoencoders (GAEs) and variational graph autoencoders (VGAEs) have been proposed to learn graph embeddings in an unsupervised way. It has been shown that these methods are effective for link prediction tasks. However, they do not work well in link predictions when a node whose degree is zero (i.g., isolated node) is involved. We have found that GAEs/VGAEs make embeddings of isolated nodes close to zero regardless of their content features. In this paper, we propose a novel Variational Graph Normalized AutoEncoder (VGNAE) that utilize L2-normalization to derive better embeddings for isolated nodes. We show that our VGNAEs outperform the existing state-of-the-art models for link prediction tasks. The code is available at https://github.com/SeongJinAhn/VGNAE.

翻译：链接预测是图形结构数据的主要问题之一。 随着图形神经网络的进步, 图形自动编码器( GAEs) 和变式图形自动编码器( VGAEs) 被提议以不受监督的方式学习图形嵌入。 已经证明这些方法对于连接预测任务是有效的。 但是, 当涉及到一个零度的节点( 例如, 孤立节点) 时, 它们在链接预测方面效果不佳。 我们发现 GAEs/ VGAEs 将孤立节点嵌入接近零, 不论其内容特性如何。 我们在此文件中提出了一个新的变形图解解解析图( 变形图) 正常自动编码器( VGNAE), 利用 L2 常规化来为孤立节点生成更好的嵌入。 我们显示, 我们的VGNAEs 超越了现有的连接预测任务状态- 艺术模型。 代码可在 https://github.com/ SeongJinAhn/ VGNAE 上查阅 。