Invariant and Equivariant Graph Networks

by   Haggai Maron, et al.

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.


page 4

page 6

page 8

page 9

page 10

page 11

page 12

page 13


Invariant Layers for Graphs with Nodes of Different Types

Neural networks that satisfy invariance with respect to input permutatio...

On Learning Sets of Symmetric Elements

Learning from unordered sets is a fundamental learning setup, which is a...

PiNet: A Permutation Invariant Graph Neural Network for Graph Classification

We propose an end-to-end deep learning learning model for graph classifi...

Graph Homomorphism Convolution

In this paper, we study the graph classification problem from the graph ...

On Universal Equivariant Set Networks

Using deep neural networks that are either invariant or equivariant to p...

Mapping Images to Scene Graphs with Permutation-Invariant Structured Prediction

Structured prediction is concerned with predicting multiple inter-depend...

Edge coherence in multiplex networks

This paper introduces a nonparametric framework for the setting where mu...

Please sign up or login with your details

Forgot password? Click here to reset