期刊名称：Bulletin of the Technical Committee on Data Engineering
出版年度：2017
卷号：40
期号：3
页码：52
出版社：IEEE Computer Society
摘要：Machine learning on graphs is an important and ubiquitous task with applications ranging from drugdesign to friendship recommendation in social networks. The primary challenge in this domain is findinga way to represent, or encode, graph structure so that it can be easily exploited by machine learningmodels. Traditionally, machine learning approaches relied on user-defined heuristics to extract featuresencoding structural information about a graph (e.g., degree statistics or kernel functions). However,recent years have seen a surge in approaches that automatically learn to encode graph structure intolow-dimensional embeddings, using techniques based on deep learning and nonlinear dimensionalityreduction. Here we provide a conceptual review of key advancements in this area of representationlearning on graphs, including matrix factorization-based methods, random-walk based algorithms, andgraph convolutional networks. We review methods to embed individual nodes as well as approachesto embed entire (sub)graphs. In doing so, we develop a unified framework to describe these recentapproaches, and we highlight a number of important applications and directions for future work.
