Megha Khosla

icon location Assistant professor at TU Delft. I develop and analyse privacy preserving and explainable graph machine learning techniques.

Results 3 comments of Megha Khosla

what does the training parameter off APP

I believe that the implementation of APP is a bit incorrect. You should also save the context embeddings as a node has two representations in the source and target role.

what does the training parameter off APP

in addition , do you know the best parameters for Cora dataset? I am unable to reproduce the paper's results for Cora even after using the context embeddings.

what does the training parameter off APP

here you go : http://konect.uni-koblenz.de/networks/subelj_cora