1
$\begingroup$

I have directed graphs with each vertex has some label in "class01_01.gml" format. There are multiple such classes. I need to do multi class classification on these files using deep learning.

Note that each graph in a particular class has different set of vertices.

Is anyone familiar how to apply deep learning in this context?

PS: I'm not that familiar in applying deep learning on graphs.

$\endgroup$

1 Answer 1

3
$\begingroup$

One of the most popular ways of doing classification on graphs is through graph convolutional networks. By running a convolution over the nodes of a graph, the neural net is able to learn the local neighborhoods of the graph. The seminal example is probably the paper Semi-Supervised Classification with Graph Convolutional Networks by Kipf and Welling. https://arxiv.org/abs/1609.02907

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge that you have read and understand our privacy policy and code of conduct.

Not the answer you're looking for? Browse other questions tagged or ask your own question.