How can I input my own graph data and compare it?

Question

How can I input my own graph data and compare it?

Lost-little-dinosaur opened this issue 2 years ago · 6 comments

Lost-little-dinosaur commented 2 years ago

Hi
I ran your train.py successfully, but I can't get an output and I want to use the script to compare my own graph data, how can I do? help me please~~.

Answer 1 · 2022-11-29T02:47:29.000Z

and of course I gave you one star [doge]

Answer 2 · 2022-11-30T02:28:06.000Z

Hi~ You could construct your own dataset in train.py. The output of the model is exactly a graph representation as shown in 66 line of train.py.

Answer 3 · 2022-11-30T04:25:24.000Z

I saw that I got the training set and the verification set in line 33, but it seemed to generate a seed, it just specified the limit range of the generated graph, and then generated an iterator through the GraphEditDistanceDataset class pairs function instead of input a concrete graph.

This is a little bit complicated for me, can you give me a concrete example where you input an adjacency matrix of two graphs, and you get an adjacency matrix of their similarity as an output? I would really appreciate it......

Answer 4 · 2022-11-30T13:10:52.000Z

Hi dinosaur~
In this repo, we give an example graph similarity learning task for synthesis graph data. It is highly expected to build your own graph dataset like GraphEditDistanceDataset. Similar to def _get_graph, you might use networkx package to change the adjacency matrix into the networkx like graph structure.

Answer 5 · 2023-02-03T05:05:19.000Z

@Lost-little-dinosaur Hi dinosaur. You could contact me with linyijie.gm@gmail.com

Answer 6 · 2023-07-21T10:08:28.000Z

hi，bro
Have you solved the problem of inputting your own graph?
Also, how was your graph generated?
Looking forward to your reply very much @Lost-little-dinosaur