Ken Liu

Hi @romovpa, thanks for the reply! Would there be a workaround for now with minor code changes?

Hi @alexandresablayrolles, thanks for the response! It seems that the API has changed for the `engine` object and `engine.step` is no longer available. Do we now apply this to the...

Hi @15762260991, Thanks for your interest! I think over-smoothing can occur whenever many GCN layers are _sequentially_ stacked together, essentially making features of neighboring nodes too similar from excessive neighborhood...

Hi @15762260991, Thanks again for your interest -- I think the term "global information" might be a bit ambiguous. Could you clarify what you meant?

Yes I think that is correct, you can set `num_scales` (https://github.com/kenziyuliu/MS-G3D/blob/master/model/ms_gcn.py#L16) to cover the entire graph in the spatial dimension. Though in Table 1 of the paper suggests that it...

Hi @whisper0411, thanks for your interest! It's been a while and I don't recall seeing this error. This looks like a simple decoding issue; maybe try re-downloading/processing the dataset, or...

Hi @adam-dziedzic, Thanks a lot for your interest! I just tried locally using the repo I cloned when writing https://github.com/google-research/federated/issues/57#issuecomment-1062468566 and it worked, but when I try re-cloning the repo...

Hi @fraboeni, Thanks for your interest! I just tried locally cloning the repo and starting a new conda environment, and I was able to get it running using the following...

Hi @fraboeni, I tried following https://github.com/google-research/federated/issues/57#issuecomment-1062468566 on a single-GPU machine, and by default things seem to work fine. Specifically, I followed https://github.com/google-research/federated/issues/57#issuecomment-1062468566, fixed the error in https://github.com/google-research/federated/issues/58, and checked that...