arXiv (Cornell University) · 2021 · 105 citations · 29 references
ComputingChemistryComputational BiologyComputational ChemistryMachine LearningDeep LearningGraph AlgorithmsGraph TheoryGraph-based LearningNetwork ModelingNeural NetworksAutoencodersDeep Learning For Molecular PropertiesDynamic Graph LearningGraph AutoencodersGraph EmbeddingsGraph Neural NetworksGraph Representation Learning
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.
29
Deep Learning On Graphs (Graphsip Summer School)
Michaël Defferrard · Figshare · 2016 · 5.1K citations
Spectral Networks and Locally Connected Networks on Graphs
Joan Bruna, Wojciech Zaremba, Arthur Szlam et al. · arXiv (Cornell University) · 2013 · 2.7K citations · Full text
Quantum chemistry structures and properties of 134 kilo molecules
Raghunathan Ramakrishnan, Pavlo O. Dral, Matthias Rupp et al. · Scientific Data · 2014 · 2K citations · Full text