Rethinking pooling in graph neural networks

10/22/2020
by   Diego Mesquita, et al.
0

Graph pooling is a central component of a myriad of graph neural network (GNN) architectures. As an inheritance from traditional CNNs, most approaches formulate graph pooling as a cluster assignment problem, extending the idea of local patches in regular grids to graphs. Despite the wide adherence to this design choice, no work has rigorously evaluated its influence on the success of GNNs. In this paper, we build upon representative GNNs and introduce variants that challenge the need for locality-preserving representations, either using randomization or clustering on the complement graph. Strikingly, our experiments demonstrate that using these variants does not result in any decrease in performance. To understand this phenomenon, we study the interplay between convolutional layers and the subsequent pooling ones. We show that the convolutions play a leading role in the learned representations. In contrast to the common belief, local pooling is not responsible for the success of GNNs on relevant and widely-used benchmarks.

READ FULL TEXT

page 6

page 18

page 19

page 20

research
06/30/2019

Mincut pooling in Graph Neural Networks

The advance of node pooling operations in a Graph Neural Network (GNN) h...
research
01/29/2022

Image Classification using Graph Neural Network and Multiscale Wavelet Superpixels

Prior studies using graph neural networks (GNNs) for image classificatio...
research
06/11/2021

Learning to Pool in Graph Neural Networks for Extrapolation

Graph neural networks (GNNs) are one of the most popular approaches to u...
research
08/15/2023

A Graph Encoder-Decoder Network for Unsupervised Anomaly Detection

A key component of many graph neural networks (GNNs) is the pooling oper...
research
03/03/2020

Graphon Pooling in Graph Neural Networks

Graph neural networks (GNNs) have been used effectively in different app...
research
10/05/2022

Bi-Stride Multi-Scale Graph Neural Network for Mesh-Based Physical Simulation

Learning physical systems on unstructured meshes by flat Graph neural ne...
research
05/01/2018

Convolutional Neural Networks Architectures for Signals Supported on Graphs

We describe two architectures that generalize convolutional neural netwo...

Please sign up or login with your details

Forgot password? Click here to reset