Reduce overfitting

I am experiencing some overfitting in my tasks and I was wondering if it is possible to add regularisation and/or dropout after the graph convolutional layers and if you have any experience on how to do it!

Thanks in advance!

Yes, you can try things like:

  • Early stopping
  • Cross validation
  • L1/L2 regularization
  • Dropout
  • Batch/Layer Normalization

to tackle the overfitting issues.