Please add implementation for HyperGCN

pyg-team / pytorch_geometric

Graph Neural Network Library for PyTorch

https://pyg.org

MIT License

21.29k stars 3.65k forks source link

Please add implementation for HyperGCN #1334

Open dtchang opened 4 years ago

dtchang commented 4 years ago

🚀 Feature

Please add implementation for HGCN (https://github.com/HazyResearch/hgcn) and HGNN (https://github.com/facebookresearch/hgnn), if feasible and at your convenience.

Motivation

From http://snap.stanford.edu/hgcn/: Graph convolutional neural networks (GCNs) map nodes in a graph to Euclidean embeddings, which have been shown to incur a large distortion when embedding real-world graphs with scale-free or hierarchical structure. Hyperbolic geometry offers an exciting alternative, as it enables embeddings with much smaller distortion.

Additional context

shaanchandra commented 4 years ago

Hi, Thanks for the solid updates in version 1.6!

I was about to request for this update as well. Just to get a rough idea, how soon (or later) can we expect this ? Will help me plan some other stuff accordingly. :)

Thanks!

rusty1s commented 4 years ago

No plans yet, sorry! If you feel like you may want to give it a go, please feel free to do so. I‘m happy to review :)

rusty1s commented 4 years ago

Maybe @RexYing can help out on this one?

RexYing commented 4 years ago

Sure will be happy to try that out.

dtchang commented 4 years ago

Great and thanks.

montellasebastien commented 2 years ago

Hello !

Any updates on adding HGCN and HGNN ?

Thanks!

rusty1s commented 2 years ago

Sadly no, sorry! We rely on community support to integrate this.