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 (35)

• Deep Learning on Graphs: A Survey
• Graph Neural Networks: Taxonomy, Advances and Trends
• Single Node Injection Attack against Graph Neural Networks
• Should Graph Convolution Trust Neighbors? A Simple Causal Inference Method
• Beyond Low-pass Filtering: Graph Convolutional Networks with Automatic Filtering
• Weisfeiler and Lehman Go Topological: Message Passing Simplicial Networks
• Path Integral Based Convolution and Pooling for Graph Neural Networks
• BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximation
• Beyond Low-Pass Filters: Adaptive Feature Propagation on Graphs
• Decimated Framelet System on Graphs and Fast G-Framelet Transforms
• Complete the Missing Half: Augmenting Aggregation Filtering with Diversification for Graph Convolutional Networks
• PAN: Path Integral Based Convolution for Deep Graph Neural Networks
• Bilinear Graph Neural Network with Neighbor Interactions
• How Framelets Enhance Graph Neural Networks
• Popularity Prediction on Social Platforms with Coupled Graph Neural Networks
• Graph Convolutional Networks using Heat Kernel for Semi-supervised Learning
• MathNet: Haar-Like Wavelet Multiresolution-Analysis for Graph Representation and Learning
• SDGNN: Learning Node Representation for Signed Directed Networks
• Deconvolutional Networks on Graph Data
• ANAE: Learning Node Context Representation for Attributed Network Embedding
• Graph Autoencoders with Deconvolutional Networks
• Self-supervised Graph Representation Learning via Bootstrapping
• Human Action Recognition with Multi-Laplacian Graph Convolutional Networks
• Exploring Structure-Adaptive Graph Learning for Robust Semi-Supervised Classification
• Heterogeneous Hypergraph Embedding for Graph Classification
• A Deep Graph Wavelet Convolutional Neural Network for Semi-supervised Node Classification
• Graph Denoising with Framelet Regularizer
• Graph Convolutional Networks in Feature Space for Image Deblurring and Super-resolution
• Framework for Designing Filters of Spectral Graph Convolutional Neural Networks in the Context of Regularization Theory
• 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
• Traffic signal prediction on transportation networks using spatio-temporal correlations on graphs
• A Block-based Generative Model for Attributed Networks Embedding
• SStaGCN: Simplified stacking based graph convolutional networks