Understanding Pooling in Graph Neural Networks

Abstract

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.

10 pages, 6 figures

References in corpus (10)

• Fast Graph Representation Learning with PyTorch Geometric
• Self-Attention Graph Pooling
• TUDataset: A collection of benchmark datasets for learning with graphs
• Edge Contraction Pooling for Graph Neural Networks
• Unsupervised Inductive Graph-Level Representation Learning via Graph-Graph Proximity
• Octree guided CNN with Spherical Kernels for 3D Point Clouds
• DEMO-Net: Degree-specific Graph Neural Networks for Node and Graph Classification
• On the Universality of Invariant Networks
• Graph Coarsening with Neural Networks
• Graph Convolutional Networks with EigenPooling

Cited by in corpus (6)

• BrainGB: A Benchmark for Brain Network Analysis with Graph Neural Networks
• Graph Deep Learning for Time Series Forecasting
• Jet tagging algorithm of graph network with HaarPooling message passing
• Simplifying Clustering with Graph Neural Networks
• A Hierarchical Framework with Spatio-Temporal Consistency Learning for Emergence Detection in Complex Adaptive Systems
• Optimised Graph Convolution for Calorimetry Event Classification