Graph Wavelet Neural Network

Abstract

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.

Cited by in corpus (14)

• Single Node Injection Attack against Graph Neural Networks
• PAN: Path Integral Based Convolution for Deep Graph Neural Networks
• Graph Convolutional Networks using Heat Kernel for Semi-supervised Learning
• Deconvolutional Networks on Graph Data
• Self-supervised Graph Representation Learning via Bootstrapping
• Graph Autoencoders with Deconvolutional Networks
• Human Action Recognition with Multi-Laplacian Graph Convolutional Networks
• A Deep Graph Wavelet Convolutional Neural Network for Semi-supervised Node Classification
• Graph Denoising with Framelet Regularizer
• Framework for Designing Filters of Spectral Graph Convolutional Neural Networks in the Context of Regularization Theory
• Graph Convolutional Networks in Feature Space for Image Deblurring and Super-resolution
• Joint Forecasting and Interpolation of Graph Signals Using Deep Learning
• Label-Consistency based Graph Neural Networks for Semi-supervised Node Classification
• Spread-gram: A spreading-activation schema of network structural learning