benedekrozemberczki / SimGNN

A PyTorch implementation of "SimGNN: A Neural Network Approach to Fast Graph Similarity Computation" (WSDM 2019).
GNU General Public License v3.0
759 stars 147 forks source link

In every epoch you get the weights/activations and turn hem into Numpy arrays. You can use a heatmap. #17

Closed Remmelt12 closed 5 years ago

Remmelt12 commented 5 years ago

In every epoch you get the weights/activations and turn hem into Numpy arrays. You can use a heatmap.

Originally posted by @benedekrozemberczki in https://github.com/benedekrozemberczki/SimGNN/issues/16#issuecomment-545666072

Could you please provide more clarification on this? The activation weights are on the output of the convolutional pass. so they are vectors of length 32. How do you get a heatmap on the graph nodes from this? Sorry I am quite new to attention so I may not fully understand how to do this