The general theory of permutation equivarant neural networks and higher order graph variational encoders

04/08/2020
by   Erik Henning Thiede, et al.
0

Previous work on symmetric group equivariant neural networks generally only considered the case where the group acts by permuting the elements of a single vector. In this paper we derive formulae for general permutation equivariant layers, including the case where the layer acts on matrices by permuting their rows and columns simultaneously. This case arises naturally in graph learning and relation learning applications. As a specific case of higher order permutation equivariant networks, we present a second order graph variational encoder, and show that the latent distribution of equivariant generative models must be exchangeable. We demonstrate the efficacy of this architecture on the tasks of link prediction in citation graphs and molecular graph generation.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/02/2021

Multiresolution Graph Variational Autoencoder

In this paper, we propose Multiresolution Graph Networks (MGN) and Multi...
research
03/25/2022

SpeqNets: Sparsity-aware Permutation-equivariant Graph Networks

While (message-passing) graph neural networks have clear limitations in ...
research
06/12/2019

Higher-Order Ranking and Link Prediction: From Closing Triangles to Closing Higher-Order Motifs

In this paper, we introduce the notion of motif closure and describe hig...
research
10/27/2021

Transformers Generalize DeepSets and Can be Extended to Graphs and Hypergraphs

We present a generalization of Transformers to any-order permutation inv...
research
06/08/2022

Set Interdependence Transformer: Set-to-Sequence Neural Networks for Permutation Learning and Structure Prediction

The task of learning to map an input set onto a permuted sequence of its...
research
12/11/2016

Baby-Step Giant-Step Algorithms for the Symmetric Group

We study discrete logarithms in the setting of group actions. Suppose th...
research
12/16/2022

Connecting Permutation Equivariant Neural Networks and Partition Diagrams

We show how the Schur-Weyl duality that exists between the partition alg...

Please sign up or login with your details

Forgot password? Click here to reset