1. PpnpPPNP & APPNP models from "Predict then Propagate: Graph Neural Networks meet Personalized PageRank" (ICLR 2019)
2. GdcGraph Diffusion Convolution, as proposed in "Diffusion Improves Graph Learning" (NeurIPS 2019)
3. DimenetDimeNet and DimeNet++ models, as proposed in "Directional Message Passing for Molecular Graphs" (ICLR 2020) and "Fast and Uncertainty-Aware Directional Message Passing for Non-Equilibrium Molecules" (NeurIPS-W 2020)