Understanding Pooling in Graph Neural Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Grattarola, Daniele, Zambon, Daniele, Bianchi, Filippo Maria, Alippi, Cesare
Format: Preprint
Published: 2021
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913280034865152
author Grattarola, Daniele
Zambon, Daniele
Bianchi, Filippo Maria
Alippi, Cesare
author_facet Grattarola, Daniele
Zambon, Daniele
Bianchi, Filippo Maria
Alippi, Cesare
contents Inspired by the conventional pooling layers in convolutional neural networks, many recent works in the field of graph machine learning have introduced pooling operators to reduce the size of graphs. The great variety in the literature stems from the many possible strategies for coarsening a graph, which may depend on different assumptions on the graph structure or the specific downstream task. In this paper we propose a formal characterization of graph pooling based on three main operations, called selection, reduction, and connection, with the goal of unifying the literature under a common framework. Following this formalization, we introduce a taxonomy of pooling operators and categorize more than thirty pooling methods proposed in recent literature. We propose criteria to evaluate the performance of a pooling operator and use them to investigate and contrast the behavior of different classes of the taxonomy on a variety of tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2110_05292
institution arXiv
publishDate 2021
record_format arxiv
spellingShingle Understanding Pooling in Graph Neural Networks
Grattarola, Daniele
Zambon, Daniele
Bianchi, Filippo Maria
Alippi, Cesare
Machine Learning
Artificial Intelligence
Inspired by the conventional pooling layers in convolutional neural networks, many recent works in the field of graph machine learning have introduced pooling operators to reduce the size of graphs. The great variety in the literature stems from the many possible strategies for coarsening a graph, which may depend on different assumptions on the graph structure or the specific downstream task. In this paper we propose a formal characterization of graph pooling based on three main operations, called selection, reduction, and connection, with the goal of unifying the literature under a common framework. Following this formalization, we introduce a taxonomy of pooling operators and categorize more than thirty pooling methods proposed in recent literature. We propose criteria to evaluate the performance of a pooling operator and use them to investigate and contrast the behavior of different classes of the taxonomy on a variety of tasks.
title Understanding Pooling in Graph Neural Networks
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2110.05292