JuliaCon 2020 (times are in UTC)

GeometricFlux.jl: Geometric Deep Learning on Flux
07-30, 13:30–14:00 (UTC), Red Track

GeometricFlux, a Julia package for geometric deep learning on graph. GeometricFlux relies on Flux/Zygote framework, integrates with JuliaGraph ecosystem and supports CUDA.


Geometric deep learning plays a role in modeling non-Euclidean data with graph structure. I introduce GeometricFlux, a Julia package for geometric deep learning on graph. GeometricFlux relies on Zygote as automatic differentiation engine, accepts graph data structure provided by JuliaGraph. GeometricFlux layers are compatible with Flux layers and supported by CuArrays. It will be a competitive platform against other framework.

I am doing my bioinformatics PhD project with machine learning/deep learning approach in Academia sinica, Taiwan. Host and founder of Julia Taiwan community.