Transcription of Representation Learning on Graphs: Methods and Applications
{{id}} {{{paragraph}}}
Example: bachelor of science
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.
decoder is a function that accepts a set of node embeddings and decodes user-specified graph statistics from these embeddings. For example, the decoder might predict the existence of edges between nodes, given their embeddings [1, 35], or it might predict the community that a node belongs to in the graph [28, 34] (Figure 3).
Loading..
Tags:
Information
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document: