Thomas Kipf

The dataset splits used in the PyGCN repository are different from the ones used in our original paper. If you would just like to reproduce the results of the original...

I think it’s best to compare the two implementations side by side if you’re interested in the precise differences (both implementations are fairly simple). For a more modern and flexible...

The dataset splits in this repository are different from the ones used in the paper / used in the TesnorFlow gcn repository. This repository is not intended as an exact...

The data splits are different, the normalization of the adjacency matrix is slightly different and there is no dropout on the first layer. On Tue 25. Sep 2018 at 10:02...

Yes, this is correct- my wording was a bit ambiguous: the original TensorFlow-based implementation also uses Dropout on the input features directly (which is what I meant by first layer)....

Yes! See https://arxiv.org/abs/1703.06103 On Thu, Jun 25, 2020 at 14:12 Alan Yang wrote: > I've only recently started working on GCN, and I've found that it usually > works on...

You can download our code for generating the Kuramoto dataset used in our paper here: https://www.dropbox.com/s/3jwim0n7iijrz9w/kuramoto.zip?dl=0 On Sat, May 9, 2020 at 5:02 AM Chen Siyuan wrote: > According to...

Have you tried setting `skip_first` to True? On Wed, Jun 3, 2020 at 11:21 AM Chen Siyuan wrote: > Your code does help. But I haven't got comparable results when...

Try re-running `python setup.py install` from the project root folder.

Thanks, I’ll leave this open so people who are interested can make use of it. To avoid clutter and to keep things simple, I prefer not to merge this into...