Directional Graph Networks

Abstract

The lack of anisotropic kernels in graph neural networks (GNNs) strongly limits their expressiveness, contributing to well-known issues such as over-smoothing. To overcome this limitation, we propose the first globally consistent anisotropic kernels for GNNs, allowing for graph convolutions that are defined according to topologicaly-derived directional flows. First, by defining a vector field in the graph, we develop a method of applying directional derivatives and smoothing by projecting node-specific messages into the field. Then, we propose the use of the Laplacian eigenvectors as such vector field. We show that the method generalizes CNNs on an $n$-dimensional grid and is provably more discriminative than standard GNNs regarding the Weisfeiler-Lehman 1-WL test. We evaluate our method on different standard benchmarks and see a relative error reduction of 8% on the CIFAR10 graph dataset and 11% to 32% on the molecular ZINC dataset, and a relative increase in precision of 1.6% on the MolPCBA dataset. An important outcome of this work is that it enables graph networks to embed directions in an unsupervised way, thus allowing a better representation of the anisotropic features in different physical or biological problems.

arXiv comment11 pages, 10 pages appendix, 6 figures, subtitle: Anisotropic aggregation in graph neural networks via directional vector fields

References in corpus (15)

• Semi-Supervised Classification with Graph Convolutional Networks
• Inductive Representation Learning on Large Graphs
• Neural Message Passing for Quantum Chemistry
• Geometric deep learning: going beyond Euclidean data
• Representation Learning on Graphs with Jumping Knowledge Networks
• Junction Tree Variational Autoencoder for Molecular Graph Generation
• Open Graph Benchmark: Datasets for Machine Learning on Graphs
• How Powerful are Graph Neural Networks?
• Residual Gated Graph ConvNets
• Principal Neighbourhood Aggregation for Graph Nets
• Benchmarking Graph Neural Networks
• On the Bottleneck of Graph Neural Networks and its Practical Implications
• Covariant Compositional Networks For Learning Graphs
• Approximation Ratios of Graph Neural Networks for Combinatorial Problems
• Graph Convolutional Neural Networks via Motif-based Attention

Cited by in corpus (3)

• Principal Neighbourhood Aggregation for Graph Nets
• Building powerful and equivariant graph neural networks with structural message-passing
• Reconstruction for Powerful Graph Representations