search

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

Dataset generation #53

Open zcyyyy24 opened 11 months ago

zcyyyy24 commented 11 months ago

Hi! Recently I have ran the model successfully, but I found the test error is so large. So I want to use other datasets to train the model, which contain more graph data. But I am confused how to generate the data that suits the training format, could you help me? Thanks a lot!