Pooling in Graph Convolutional Neural Networks
Signal Processing
2020-04-08 v1 Machine Learning
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.
Cite
@article{arxiv.2004.03519,
title = {Pooling in Graph Convolutional Neural Networks},
author = {Mark Cheung and John Shi and Lavender Yao Jiang and Oren Wright and José M. F. Moura},
journal= {arXiv preprint arXiv:2004.03519},
year = {2020}
}
Comments
5 pages, 2 figures, 2019 Asilomar Conference paper