학술논문
Pooling in Graph Convolutional Neural Networks
Document Type
Conference
Source
2019 53rd Asilomar Conference on Signals, Systems, and Computers Signals, Systems, and Computers, 2019 53rd Asilomar Conference on. :462-466 Nov, 2019
Subject
Language
ISSN
2576-2303
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.