Graph2vec for graph similarity learning

[smith-co]

I am thinking to use Graph2vec for learning graph similarity learning.

Given two graphs, I am thinking to get embeddings of the two graphs and then take the cosine similarity of the two graphs.

May graphs would have around 5000 nodes and 4000 edges.

Is Graph2vec a good fit for this task?

[benedekrozemberczki]

Dear @smith-co,

Could you star the repo first?

Yes it is! I would recommend using the Karateclub implementation!

https://github.com/benedekrozemberczki/karateclub

Bests,

Benedek

[smith-co]

@benedekrozemberczki of course - added star to the repo :-)

I am looking into the Karateclub repo. Can you please point me how to create the API to create graphs for Karateclub?

[smith-co]

@benedekrozemberczki do you have an example where you build a graph from scratch i.e. create nodes and then add edges?