论文标题
汇总图中卷积神经网络
Pooling in Graph Convolutional Neural Networks
论文作者
论文摘要
图形卷积神经网络(GCNN)是深度学习技术到图形结构数据问题的有力扩展。我们从经验上评估了GCNN的几种合并方法,以及这些图形合并方法与三种不同架构的组合:GCN,TAGCN和GraphSage。我们确认图形合并,尤其是Diffpool,提高了流行的图形分类数据集的分类精度,并发现TAGCN平均具有比GCN和Graphsage相当或更好的精度,尤其是对于具有较大且稀疏图结构的数据集。
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.