Pooling in Graph Convolutional Neural Networks

2020/04/07 by Mark Cheung, Cheung, Mark, Shi, John +6 · 1 citation
Computer Science · #Advanced Graph Neural Networks #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Signal Processing (eess.SP) #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2004.03519

openalex publication_date 2020/04/07 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Graph convolutional neural networks (GCNNs) are a powerful extension of deep learning techniques to graph-structured data problems. We empirically evaluate several pooling methods for GCNNs, and combinations of those graph pooling methods with three different architectures: GCN, TAGCN, and GraphSAGE. We confirm that graph pooling, especially DiffPool, improves classification accuracy on popular graph classification datasets and find that, on average, TAGCN achieves comparable or better accuracy than GCN and GraphSAGE, particularly for datasets with larger and sparser graph structures.

Citations

• Wavelets on graphs via spectral graph theory
• Semi-Supervised Classification with Graph Convolutional Networks
• Geometric Deep Learning: Going beyond Euclidean data
• Topology Adaptive Graph Convolutional Networks
• Fast Graph Representation Learning with PyTorch Geometric

Cited by

• Weaver: Kronecker Product Approximations of Spatiotemporal Attention for Traffic Network Forecasting

Related

• Rethinking pooling in graph neural networks
• Graph Convolutional Networks with EigenPooling
• Clique pooling for graph classification
• Graph Pooling for Graph Neural Networks: Progress, Challenges, and Opportunities
• Careful Selection and Thoughtful Discarding: Graph Explicit Pooling Utilizing Discarded Nodes