GeometricFlux.jl
GeometricFlux.jl copied to clipboard
FluxML
Geometric Deep Learning for Flux
- [ ] `GraphWavelet` layer - [ ] `GWNN` example > [benedekrozemberczki/GraphWaveletNeuralNetwork](https://github.com/benedekrozemberczki/GraphWaveletNeuralNetwork) > Ref. [Graph Wavelet Neural Network](https://arxiv.org/abs/1904.07785)
> [snap-stanford/graphwave](https://github.com/snap-stanford/graphwave) > Ref. [Learning Structural Node Embeddings via Diffusion Wavelets](https://dl.acm.org/doi/10.1145/3219819.3220025)
Hello, I'm new to `GeometricFlux` and currently experimenting with its features. I just ran into the following issue: when I use a directed graph as input of a `GraphConv` layer,...
- [x] `EquivGraphConv` layer - [ ] `EGNN` network and example > Ref. [E(n) Equivariant Graph Neural Networks](https://arxiv.org/abs/2102.09844)
Since GNN lack of canonical positional information, it reduces the expressiveness of a GNN model and cannot reach ideal task performance. It is a must to support positional encoding for...
Geometric Algebra, also known as Clifford Algebra, is a natural mathematical language for geometric applications (as the name would imply). Although this is certainly a non-trivial addition to the package,...
- [ ] `LieAlgConv` layer - [ ] `LACN` model > Ref. [Automatic Symmetry Discovery with Lie Algebra Convolutional Network](https://papers.nips.cc/paper/2021/hash/148148d62be67e0916a833931bd32b26-Abstract.html)
> Ref. [Neural Jacobian Fields: Learning Intrinsic Mappings of Arbitrary Meshes](https://arxiv.org/abs/2205.02904)
* [FabianFuchsML/se3-transformer-public](https://github.com/FabianFuchsML/se3-transformer-public) * [SE3Transformer](https://github.com/NVIDIA/DeepLearningExamples/tree/master/DGLPyTorch/DrugDiscovery/SE3Transformer) > Ref. [SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networks](https://proceedings.neurips.cc/paper/2020/file/15231a7ce4ba789d13b722cc5c955834-Paper.pdf)
I was wondering if this package is based on the [geometric deep learning](https://geometricdeeplearning.com/) by Michael Bronstein et.al.? Can this package do the 5G(Grids,Graphs,Groups,Geodesics&Gauges) thing? Is it possible to add [a...
