alexduvalinho/graphsvx

Explanation method for Graph Neural Networks (GNNs)

graphsvx's Issues

Is GraphSVX usable for graph regression ?

Can I use your package to explain a model taking a graph in input and predicting a graph score?

Is GraphSVX applicable to node regression tasks? (GNNs that predict a numerical value on the nodes of a graph)

Explanation Accuracy on MUTAG

Dear authors,

thanks for your interesting work and sharing the code! I have tried the code and encountered the problem when using GraphSVX on the MUTAG dataset. I have only reached the explanation accuracy of 0.1.
I trained a GCN/GNN on MUTAG using your training script, but my model also has lower accuracy (10% lower) than your result reported in the paper. So it could be that my model is not well trained.

Could you please provide the hyperparams that you used for training the model, as well as the evaluating in explanation for MUTAG?

Thank you very much for your help in advance!

Best,

I don't know how this code works

Hi,
I don't know how this code works, how can I get the model of GraphSVX, can you record a running video, thank you very much.
If I run the script_train.py,the error is

model = eval(args.model)(input_dim=data.num_features, output_dim=data.num_classes, **eval(hyperparam))
File "", line 1, in
NameError: name 'GAT' is not defined
can you help me

Explanation Accuracy Much Lower Than Table in Paper for syn2/syn4/syn5

Dear authors,
Thank you for sharing the code. I am trying to run your code to reproduce the results reported in your paper. I downloaded the project, unzip it, and then run
python3 script_eval_gt.py --dataset synX
with X equals 1, 2, 4, and 5, without changing anything in the project. With the dataset syn1, I got node accuracy 0.99, which matches the number in Table 1. However, I got node accuracy 0.62/0.61/0.51 for syn2/syn4/syn5, which are much lower than the 0.93/0.97/0.93 in Table 1 for these three cases.
Did I misinterpret anything? Are there something special about syn2/syn4/syn5 datasets that I should modify before I can get the same results as Table 1? Thank you! Your response/help is greatly appreciated.

Environment requirements

Hi,
I wanna reproduce your work and I am trying to set up the environment. Although I use the requirements.txt to install, it seems that there is an error that says "AttributeError: 'GATConv' object has no attribute 'lin_src'". Currently, I am using python==3.7.2, torch==1.10.1+cu113, torch-geometric==2.0.3 ,torchvision==0.11.2+cu113, tensorboardX==2.5 and seaborn==0.10.1. Could you please tell me the environment that you set up? Thx!

Is it useable for heterogeneous graph?

Dear authors,

I am wondering is GraphSVX also useable for heterogeneous graphs? Thanks