Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking
Nov 03, 2017 (modified: Dec 04, 2017)ICLR 2018 Conference Blind Submissionreaders: everyoneShow Bibtex
Abstract: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 low-dimensional continuous space, we embed each node as a Gaussian distribution, allowing us to capture uncertainty about the representation. Furthermore, we propose an unsupervised method that handles inductive learning scenarios and is applicable to different types of graphs (plain/attributed, directed/undirected). By leveraging both the 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 of 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. Additionally, we demonstrate the benefits of modeling uncertainty -- by analyzing it we can estimate neighborhood diversity and detect the intrinsic latent dimensionality of a graph.
TL;DR: We embed nodes in a graph as Gaussian distributions allowing us to capture uncertainty about their representation.
Keywords:node embeddings, graphs, unsupervised learning, inductive learning, uncertainty, deep learning
Enter your feedback below and we'll get back to you as soon as possible.