Log In Sign Up

Directional Graph Networks

by   Dominique Beaini, et al.

In order to overcome the expressive limitations of graph neural networks (GNNs), we propose the first method that exploits vector flows over graphs to develop globally consistent directional and asymmetric aggregation functions. We show that our directional graph networks (DGNs) generalize convolutional neural networks (CNNs) when applied on a grid. Whereas recent theoretical works focus on understanding local neighbourhoods, local structures and local isomorphism with no global information flow, our novel theoretical framework allows directional convolutional kernels in any graph. 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, and 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. Finally, we bring the power of CNN data augmentation to graphs by providing a means of doing reflection, rotation and distortion on the underlying directional field. We evaluate our method on different standard benchmarks and see a relative error reduction of 8% on the CIFAR10 graph dataset and 11 this work is that it enables to translate any physical or biological problems with intrinsic directional axes into a graph network formalism with an embedded directional field.


A Hierarchy of Graph Neural Networks Based on Learnable Local Features

Graph neural networks (GNNs) are a powerful tool to learn representation...

Motif Graph Neural Network

Graphs can model complicated interactions between entities, which natura...

Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernels

While graph kernels (GKs) are easy to train and enjoy provable theoretic...

Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting

While Graph Neural Networks (GNNs) have achieved remarkable results in a...

SpherePHD: Applying CNNs on a Spherical PolyHeDron Representation of 360 degree Images

Omni-directional cameras have many advantages over conventional cameras ...

A Scalable Evolution Strategy with Directional Gaussian Smoothing for Blackbox Optimization

We developed a new scalable evolution strategy with directional Gaussian...

Is the U-Net Directional-Relationship Aware?

CNNs are often assumed to be capable of using contextual information abo...