Open CarloLucibello opened 2 years ago
Would it be possible to also have a list of wished-for-algorithms, included or not in DGL? :-) For example I'd love to see edge-featured-based algorithms in general, and maybe more specifically the "Exploiting Edge Features in Graph Neural Networks" from .https://arxiv.org/abs/1809.02709
Of course! You can file a separate issue for each feature request and I'll try to get to them as soon as I can spare some time if no one beats me to it. For instance, "Exploiting Edge Features in Graph Neural Networks" seems to be cited enough that it is worth having, so you are welcome to open a new issue.
Perfect! :-)
Checklist of stuff we miss compared to Deep Graph Library. PRs are welcome!
Conv Layers
GCNConv
here)Dense Conv Layers
Global Pooling Layers
GlobalPooling(+)
here)GlobalPooling(mean)
here)GlobalPooling(max)
here)Batching and Reading Out Ops
https://docs.dgl.ai/en/0.6.x/api/python/dgl.html#batching-and-reading-out-ops
Flux.batch
orSparseArrays.blockdiag
reduce_nodes
here)reduce_edges
here)Adjacency Related Utilities
nn.functional
https://docs.dgl.ai/api/python/nn.functional.html
softmax_edge_neighbors
here)optim
https://docs.dgl.ai/api/python/dgl.optim.html
nn Utility Modules
GNNChain
here)nn NodeEmbedding Module
Sampling and Stochastic training
.....
Distributed Training
....