Graph based models for machine learning on atomic systems!

AtomicGraphNets implements a variety of graph-based methods, such as Crystal Graph Convolutional Neural Nets; in Julia.
It makes use of the Flux ecosystem for model building, the JuliaGraphs ecosystem for graph representation, and ChemistryFeaturization for building, featurizing, and visualizing the graphs.

This package is in development as part of the ACED project, funded by ARPA-E DIFFERENTIATE and coordinated by Carnegie Mellon University, in collaboration with Julia Computing, Citrine Informatics, and MIT.