Geometric Graph Representations and Geometric Graph Convolutions for Deep Learning on Three-Dimensional (3D) Graphs
arXiv:2006.01785
Abstract
The geometry of three-dimensional (3D) graphs, consisting of nodes and edges, plays a crucial role in many important applications. An excellent example is molecular graphs, whose geometry influences important properties of a molecule including its reactivity and biological activity. To facilitate the incorporation of geometry in deep learning on 3D graphs, we define three types of geometric graph representations: positional, angle-geometric and distance-geometric. For proof of concept, we use the distance-geometric graph representation for geometric graph convolutions. Further, to utilize standard graph convolution networks, we employ a simple edge weight / edge distance correlation scheme, whose parameters can be fixed using reference values or determined through Bayesian hyperparameter optimization. The results of geometric graph convolutions, for the ESOL and Freesol datasets, show significant improvement over those of standard graph convolutions. Our work demonstrates the feasibility and promise of incorporating geometry, using the distance-geometric graph representation, in deep learning on 3D graphs.
References in corpus (7)
- Practical Bayesian Optimization of Machine Learning Algorithms
- Fast Graph Representation Learning with PyTorch Geometric
- A Tutorial on Bayesian Optimization
- Three-Dimensionally Embedded Graph Convolutional Network (3DGCN) for Molecule Interpretation
- Bayesian Optimization for Machine Learning : A Practical Guidebook
- Bayesian Hyperparameter Optimization with BoTorch, GPyTorch and Ax
- Tiered Graph Autoencoders with PyTorch Geometric for Molecular Graphs