Permutation-Invariant Variational Autoencoder for Graph-Level Representation Learning

04/20/2021
by   Robin Winter, et al.
0

Recently, there has been great success in applying deep neural networks on graph structured data. Most work, however, focuses on either node- or graph-level supervised learning, such as node, link or graph classification or node-level unsupervised learning (e.g. node clustering). Despite its wide range of possible applications, graph-level unsupervised learning has not received much attention yet. This might be mainly attributed to the high representation complexity of graphs, which can be represented by n! equivalent adjacency matrices, where n is the number of nodes. In this work we address this issue by proposing a permutation-invariant variational autoencoder for graph structured data. Our proposed model indirectly learns to match the node ordering of input and output graph, without imposing a particular node ordering or performing expensive graph matching. We demonstrate the effectiveness of our proposed model on various graph reconstruction and generation tasks and evaluate the expressive power of extracted representations for downstream graph-level classification and regression.

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
11/19/2019

Heterogeneous Deep Graph Infomax

Graph representation learning is to learn universal node representations...
research
05/27/2019

Incidence Networks for Geometric Deep Learning

One may represent a graph using both its node-edge and its node-node inc...
research
12/03/2022

Interpretable Node Representation with Attribute Decoding

Variational Graph Autoencoders (VGAEs) are powerful models for unsupervi...
research
09/07/2021

Scale-invariant representation of machine learning

The success of machine learning stems from its structured data represent...
research
04/30/2015

Lateral Connections in Denoising Autoencoders Support Supervised Learning

We show how a deep denoising autoencoder with lateral connections can be...
research
10/09/2020

Dirichlet Graph Variational Autoencoder

Graph Neural Networks (GNNs) and Variational Autoencoders (VAEs) have be...

Please sign up or login with your details

Forgot password? Click here to reset