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.

Incontrast,representation learning approaches treat this problem as machine learning task itself, using a data-driven approach to learn embeddings that encode graph structure. Here we provide an overview of recent advancements in representation learning on graphs, reviewing tech-niques for representing both nodes and entire subgraphs.

Loading..

Tags:

  Learning, Representation, Graph, Representation learning

Information

Related search queries