Graph Wavelet Neural Network

We present graph wavelet neural network (GWNN), a novel graph convolutional neural network (CNN), leveraging graph wavelet transform to address the shortcomings of previous spectral graph CNN methods that depend on graph Fourier transform. Different from graph Fourier transform, graph wavelet transform can be obtained via a fast algorithm without requiring matrix eigendecomposition with high computational cost. Moreover, graph wavelets are sparse and localized in vertex domain, offering high efficiency and good interpretability for graph convolution. The proposed GWNN significantly outperforms previous spectral graph CNNs in the task of graph-based semi-supervised classification on three benchmark datasets: Cora, Citeseer and Pubmed.

PDF Abstract ICLR 2019 PDF ICLR 2019 Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Node Classification Citeseer GWNN Accuracy 71.7% # 53
Node Classification Cora GWNN Accuracy 81.6% # 60
Node Classification Pubmed GWNN Accuracy 79.1% # 51

Methods


No methods listed for this paper. Add relevant methods here