Methods that learn representations of graph nodes play a critical role in network analysis since they enable many downstream learning tasks. We propose Graph2Gauss - an approach that can efficiently learn versatile node embeddings on large scale (attributed) graphs that show strong performance on tasks such as link prediction and node classification. Unlike most approaches that represent nodes as (point) vectors in a lower-dimensional continuous space, we embed each node as a Gaussian distribution, allowing us to capture uncertainty about the representation. Furthermore, in contrast to previous approaches we propose a completely unsupervised method that is also able to handle inductive learning scenarios and is applicable to different types of graphs (plain, attributed, directed, undirected). By leveraging both the topological network structure and the associated node attributes, we are able to generalize to unseen nodes without additional training. To learn the embeddings we adopt a personalized ranking formulation w.r.t. the node distances that exploits the natural ordering between the nodes imposed by the network structure. Experiments on real world networks demonstrate the high performance of our approach, outperforming state-of-the-art network embedding methods on several different tasks.

Graph2Gauss是一种利用高斯分布表示节点，可以快速有效地在大规模（带属性）图上学习多功能节点嵌入，并且优于现有的方法，在网络分析和不同类型的图上都适用的无监督学习方法。

图的深度高斯嵌入：通过排名进行无监督归纳学习