Invariant and Equivariant Graph Networks

TL;DR

This paper characterizes all permutation invariant and equivariant linear layers for graph data, providing bases and dimensions, and demonstrates their effectiveness and generality in graph neural networks.

Contribution

It offers a complete characterization of invariant and equivariant linear layers for graphs, including bases and dimensions, unifying recent advances and enhancing expressivity.

Findings

Dimension of invariant layers is 2 for edge-value graphs.

Dimension of equivariant layers is 15 for edge-value graphs.

Networks using these layers achieve competitive results and improved expressivity.

Abstract

Invariant and equivariant networks have been successfully used for learning images, sets, point clouds, and graphs. A basic challenge in developing such networks is finding the maximal collection of invariant and equivariant linear layers. Although this question is answered for the first three examples (for popular transformations, at-least), a full characterization of invariant and equivariant linear layers for graphs is not known. In this paper we provide a characterization of all permutation invariant and equivariant linear layers for (hyper-)graph data, and show that their dimension, in case of edge-value graph data, is 2 and 15, respectively. More generally, for graph data defined on k-tuples of nodes, the dimension is the k-th and 2k-th Bell numbers. Orthogonal bases for the layers are computed, including generalization to multi-graph data. The constant number of basis elements and their characteristics allow successfully applying the networks to different size graphs. From the theoretical point of view, our results generalize and unify recent advancement in equivariant deep learning. In particular, we show that our model is capable of approximating any message passing neural network Applying these new linear layers in a simple deep neural network framework is shown to achieve comparable results to state-of-the-art and to have better expressivity than previous invariant and equivariant bases.