Equivariant Neural Operator Learning with Graphon Convolution
Preprint
Abstract
We propose a general architecture that combines the coefficient learning scheme with a residual operator layer for learning mappings between continuous functions in the 3D Euclidean space. Our proposed model is guaranteed to achieve SE(3)-equivariance by design. From the graph spectrum view, our method can be interpreted as convolution on graphons (dense graphs with infinitely many nodes), which we term InfGCN. By leveraging both the continuous graphon structure and the discrete graph structure of the input data, our model can effectively capture the geometric information while preserving equivariance. Through extensive experiments on large-scale electron density datasets, we observed that our model significantly outperformed the current state-of-the-art architectures. Multiple ablation studies were also carried out to demonstrate the effectiveness of the proposed architecture.Keywords
All Related Versions
This publication has 30 references indexed in Scilit:
- Predicting accurate ab initio DNA electron densities with equivariant neural networksBiophysical Journal, 2022
- Prediction of the Electron Density of States for Crystalline Compounds with Atomistic Line Graph Neural Networks (ALIGNN)JOM, 2022
- Deep Density: Circumventing the Kohn-Sham equations via symmetry preserving neural networksJournal of Computational Physics, 2021
- Direct Prediction of Phonon Density of States With Euclidean Neural NetworksAdvanced Science, 2021
- SphereNet: Learning Spherical Representations for Detection and Classification in Omnidirectional Images2018
- Bypassing the Kohn-Sham equations with machine learningNature Communications, 2017
- 3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Enumeration of 166 Billion Organic Small Molecules in the Chemical Universe Database GDB-17Journal of Chemical Information and Modeling, 2012
- THE NATURE OF THE CHEMICAL BOND. APPLICATION OF RESULTS OBTAINED FROM THE QUANTUM MECHANICS AND FROM A THEORY OF PARAMAGNETIC SUSCEPTIBILITY TO THE STRUCTURE OF MOLECULESJournal of the American Chemical Society, 1931