Clique pooling for graph classification

03/31/2019
by   Enxhell Luzhnica, et al.
0

We propose a novel graph pooling operation using cliques as the unit pool. As this approach is purely topological, rather than featural, it is more readily interpretable, a better analogue to image coarsening than filtering or pruning techniques, and entirely nonparametric. The operation is implemented within graph convolution network (GCN) and GraphSAGE architectures and tested against standard graph classification benchmarks. In addition, we explore the backwards compatibility of the pooling to regular graphs, demonstrating competitive performance when replacing two-by-two pooling in standard convolutional neural networks (CNNs) with our mechanism.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

04/07/2020

Pooling in Graph Convolutional Neural Networks

Graph convolutional neural networks (GCNNs) are a powerful extension of ...
04/17/2019

Self-Attention Graph Pooling

Advanced methods of applying deep learning to structured data such as gr...
08/23/2021

Understanding the Basis of Graph Convolutional Neural Networks via an Intuitive Matched Filtering Approach

Graph Convolutional Neural Networks (GCNN) are becoming a preferred mode...
05/01/2018

Convolutional Neural Networks Architectures for Signals Supported on Graphs

We describe two architectures that generalize convolutional neural netwo...
12/28/2020

LookHops: light multi-order convolution and pooling for graph classification

Convolution and pooling are the key operations to learn hierarchical rep...
12/14/2021

Graph Kernel Neural Networks

The convolution operator at the core of many modern neural architectures...
05/09/2019

Convolutional Neural Networks Utilizing Multifunctional Spin-Hall MTJ Neurons

We propose a new network architecture for standard spin-Hall magnetic tu...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.