About DGCNN hyper-parameter

[KailiangGu]

Hi, Dr. Zhang

I have a question regarding to the DGCNN hyper-parameter "cmd_args.feat_dim". It seems like this parameter is set to 16. May I ask what is this parameter is used for? I was trying to run test on my data, and I run into an error. In main.py line 87, the concat_tage contains values greater than 16, which it lead to invalid index error when the "node_tag.scatter_(1, concat_tag, 1)" is called. Is there any suggestion that can help me solve this problem?

Thanks.

[muhanzhang]

Hi! In this line, "cmd_args.feat_dim" is set to the maximum node label + 1. This is because we transform the integer node labels into one-hot encodings.

Your problem might be caused by your testing graphs have a maximum node label larger than that of the training graphs. In this case, you can manually set "cmd_args.feat_dim" to your testing graphs' maximum node label, and retrain your model.