0
$\begingroup$

I have N graphs, they all have same topology,but they differ in vertices weight. I would like to cluster these graphs such that graphs that their vertices has similar weights in similar positions are in same cluster. Initially I was thinking to vectorize graphs(every element of vector is one vertice) and compute euclidian distances of them. But this does not take the topology of graph into account Would someone can help me with this?

$\endgroup$
0
$\begingroup$

You could vectorize the graph and do co-ordinate wise clustering i.e., apply Euclidian distance clustering for each coordinate

$\endgroup$
  • $\begingroup$ would you please explain more what do you mean by that. $\endgroup$ – user2806363 Oct 15 '17 at 7:42

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

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