E(n) Equivariant Graph Neural Networks

作者：Victor Garcia Satorras, E. Hoogeboom, M. Welling · 发表于：International Conference on Machine Learning · 年份：2021 · 被引用次数：1616 · 研究领域：Computer Science、Mathematics

This paper introduces a new model to learn graph neural networks equivariant to rotations, translations, reflections and permutations called E(n)-Equivariant Graph Neural Networks (EGNNs). In contrast with existing methods, our work does not require computationally expensive higher-order representations in intermediate layers while it still achieves competitive or better performance. In addition, whereas existing methods are limited to equivariance on 3 dimensional spaces, our model is easily scaled to higher-dimensional spaces. We demonstrate the effectiveness of our method on dynamical systems modelling, representation learning in graph autoencoders and predicting molecular properties.