Wavelet scattering transforms on graphs via PyTorch

gsxform is a package for constructing graph scattering transforms, leveraging PyTorch to allow for GPU based computation. Using PyTorch, gsxform offers the ability to more easily build models that use both scattering transform and neural network components.

gsxform is first and foremost a research project and is being continuously refined. Behavior can potentially be unstable and consistency is not guaranteed.

gsxform is available on PyPi:

pip install gsxform

The most up-to-date version of gsxform can be installed via git:

pip install git+https://github.com/armaank/gsxform.git

The original code of this repository is released under the BSD 3.0-Clause Licence. Modifications, adaptations and derivative work is encouraged!

If you use gsxform, please cite using the Zenodo DOI