Representation Learning on Graphs: Methods and Applications

Representation Learning on Graphs: Methods and ApplicationsWilliam L. of Computer ScienceStanford UniversityStanford, CA, 94305 AbstractMachine 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 ( , 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.

To extract structural information from graphs, traditional machine approaches often rely on summary graph statistics (e.g., degrees or clustering coefficients) [6], kernel functions [57], or carefully engineered features to measure local neighborhood structures [39]. However, these approaches are limited because these hand-

Loading..

Tags:

  Statistics, Learning, Graph, Graph statistics

Information

Related search queries