E(n) Equivariant Graph Neural Networks

Vı́ctor Garcia Satorras, Emiel Hoogeboom, Max Welling
Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9323-9332, 2021.

Abstract

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v139-satorras21a, title = {E(n) Equivariant Graph Neural Networks}, author = {Satorras, V\'{\i}ctor Garcia and Hoogeboom, Emiel and Welling, Max}, booktitle = {Proceedings of the 38th International Conference on Machine Learning}, pages = {9323--9332}, year = {2021}, editor = {Meila, Marina and Zhang, Tong}, volume = {139}, series = {Proceedings of Machine Learning Research}, month = {18--24 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v139/satorras21a/satorras21a.pdf}, url = {https://proceedings.mlr.press/v139/satorras21a.html}, abstract = {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.} }
Endnote
%0 Conference Paper %T E(n) Equivariant Graph Neural Networks %A Vı́ctor Garcia Satorras %A Emiel Hoogeboom %A Max Welling %B Proceedings of the 38th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2021 %E Marina Meila %E Tong Zhang %F pmlr-v139-satorras21a %I PMLR %P 9323--9332 %U https://proceedings.mlr.press/v139/satorras21a.html %V 139 %X 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.
APA
Satorras, V.G., Hoogeboom, E. & Welling, M.. (2021). E(n) Equivariant Graph Neural Networks. Proceedings of the 38th International Conference on Machine Learning, in Proceedings of Machine Learning Research 139:9323-9332 Available from https://proceedings.mlr.press/v139/satorras21a.html.

Related Material