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

training data #24

Closed jonathan-goh closed 4 years ago

jonathan-goh commented 4 years ago

Hi there,

I'm looking at your description on how to prepare the training data is prepared in json

{"graph_1": [[0, 1],[1, 2],[2, 3],[3, 4]], "graph_2": [[0, 1], [1, 2], [1, 3], [3, 4], [2, 4]], "labels_1": [2, 2, 2, 2], "labels_2": [2, 3, 2, 3], "ged": 1}

I am trying to get my head around how the labels of the nodes are supposed to be. I understand that the lists in both graph_1 and graph_2 are the edges . Graph_1 have 4 edges and graph_2 have 5 edges. But how is it that both labels have 4 nodes?

are you able to show how do these graphs actually look like? Thanks.

benedekrozemberczki commented 4 years ago

Corrected the description.