Scalable training of graph convolutional neural networks for fast and accurate predictions of HOMO-LUMO gap in molecules.
Jong Youl ChoiPei ZhangKshitij MehtaAndrew BlanchardMassimiliano Lupo PasiniPublished in: CoRR (2022)
Keyphrases
- convolutional neural networks
- random walk
- graph representation
- training set
- supervised learning
- directed graph
- graph structure
- bipartite graph
- convolutional network
- chemical compounds
- graph theoretic
- training phase
- graph model
- training examples
- neural network
- graph mining
- data sets
- test set
- training samples
- multiscale