PiNet: A Permutation Invariant Graph Neural Network for Graph Classification

05/08/2019
by   Peter Meltzer, et al.
20

We propose an end-to-end deep learning learning model for graph classification and representation learning that is invariant to permutation of the nodes of the input graphs. We address the challenge of learning a fixed size graph representation for graphs of varying dimensions through a differentiable node attention pooling mechanism. In addition to a theoretical proof of its invariance to permutation, we provide empirical evidence demonstrating the statistically significant gain in accuracy when faced with an isomorphic graph classification task given only a small number of training examples. We analyse the effect of four different matrices to facilitate the local message passing mechanism by which graph convolutions are performed vs. a matrix parametrised by a learned parameter pair able to transition smoothly between the former. Finally, we show that our model achieves competitive classification performance with existing techniques on a set of molecule datasets.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/02/2020

Permutation Invariant Graph Generation via Score-Based Generative Modeling

Learning generative models for graph-structured data is challenging beca...
research
01/04/2022

Graph Decipher: A transparent dual-attention graph neural network to understand the message-passing mechanism for the node classification

Graph neural networks can be effectively applied to find solutions for m...
research
07/22/2019

IsoNN: Isomorphic Neural Network for Graph Representation Learning and Classification

Deep learning models have achieved huge success in numerous fields, such...
research
12/24/2018

Invariant and Equivariant Graph Networks

Invariant and equivariant networks have been successfully used for learn...
research
01/07/2018

Covariant Compositional Networks For Learning Graphs

Most existing neural networks for learning graphs address permutation in...
research
04/01/2018

Attentional Multilabel Learning over Graphs - A message passing approach

We address a largely open problem of multilabel classification over grap...
research
08/14/2017

Graph Classification via Deep Learning with Virtual Nodes

Learning representation for graph classification turns a variable-size g...

Please sign up or login with your details

Forgot password? Click here to reset