GeometricFlux.jl
GeometricFlux.jl copied to clipboard
Geometric Deep Learning for Flux
I tried to run the Semi-Supervised GCN example and it appears to be broken. The issue is that the loss and accuracy functions don't seem to work with the DataLoader....
> Ref. [Design Space for Graph Neural Networks](https://arxiv.org/abs/2011.08843)
> Ref. [Vector Neurons: A General Framework for SO(3)-Equivariant Networks](https://arxiv.org/abs/2104.12229)
Having trouble using a SimpleWeightedGraph as input for the GCNConv-layer. My graph is an undirected simple Int64 graph with Float64 weights and calling adjacency_matrix() on this works fine. But during...
> Ref. [GRAND: Graph Neural Diffusion](https://arxiv.org/abs/2106.10934)
> Ref. [Wavelet Networks: Scale Equivariant Learning From Raw Waveforms](https://arxiv.org/abs/2006.05259)
- [ ] `GConv` layer (G-convolution) - [ ] `GPool` layer (G-pooling) - [ ] `GCNN` example > Ref. [Group Equivariant Convolutional Networks](http://proceedings.mlr.press/v48/cohenc16.html)
> Ref. [Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks](https://arxiv.org/abs/1905.07953)
> Ref. [Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling](https://aclanthology.org/D17-1159/)
> Ref. [FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling](https://arxiv.org/abs/1801.10247)