Symmetry-driven graph neural networks

Abstract

Exploiting symmetries and invariance in data is a powerful, yet not fully exploited, way to achieve better generalisation with more efficiency. In this paper, we introduce two graph network architectures that are equivariant to several types of transformations affecting the node coordinates. First, we build equivariance to any transformation in the coordinate embeddings that preserves the distance between neighbouring nodes, allowing for equivariance to the Euclidean group. Then, we introduce angle attributes to build equivariance to any angle preserving transformation - thus, to the conformal group. Thanks to their equivariance properties, the proposed models can be vastly more data efficient with respect to classical graph architectures, intrinsically equipped with a better inductive bias and better at generalising. We demonstrate these capabilities on a synthetic dataset composed of $n$-dimensional geometric objects. Additionally, we provide examples of their limitations when (the right) symmetries are not present in the data.

References in corpus (15)

• Adam: A Method for Stochastic Optimization
• Neural Message Passing for Quantum Chemistry
• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
• Group Equivariant Convolutional Networks
• Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds
• Learning to Simulate Complex Physics with Graph Networks
• Benchmarking Graph Neural Networks
• E(n) Equivariant Graph Neural Networks
• Physical Symmetries Embedded in Neural Networks
• MoleculeNet: A Benchmark for Molecular Machine Learning
• A Practical Method for Constructing Equivariant Multilayer Perceptrons for Arbitrary Matrix Groups
• Learning with invariances in random features and kernel models
• Beyond permutation equivariance in graph networks