I'm a student who just start study deep learning.

I hope to practice with simple project using Graph Convolution Network.

The question is that "How can I handle with different size of input graph for GCN?"

Padding with zero is the only way to handle this problem? And zero padding like CNN is proper also for GCN?


  • $\begingroup$ I hope to study about molecule or protein with graph convolutional network! $\endgroup$ – Newbie1111 Dec 3 '19 at 17:03
  • $\begingroup$ Zero-padding is the most common way. You might find a good approach in this paper: arxiv.org/pdf/1808.03965.pdf which is designed for large-scale cases $\endgroup$ – aminrd Dec 4 '19 at 0:46
  • $\begingroup$ Thanks for suggestion! $\endgroup$ – Newbie1111 Dec 4 '19 at 15:52

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.