A Deep Graph Wavelet Convolutional Neural Network for Semi-supervised Node Classification
This work addresses a bottleneck in graph neural networks for researchers and practitioners, offering an incremental improvement over existing methods.
The authors tackled the problem of over-smoothing in deep graph convolutional networks for semi-supervised node classification by proposing DeepGWC, which integrates wavelet transforms with Fourier bases and residual connections, achieving state-of-the-art performance on benchmark datasets like Cora, Citeseer, and Pubmed.
Graph convolutional neural network provides good solutions for node classification and other tasks with non-Euclidean data. There are several graph convolutional models that attempt to develop deep networks but do not cause serious over-smoothing at the same time. Considering that the wavelet transform generally has a stronger ability to extract useful information than the Fourier transform, we propose a new deep graph wavelet convolutional network (DeepGWC) for semi-supervised node classification tasks. Based on the optimized static filtering matrix parameters of vanilla graph wavelet neural networks and the combination of Fourier bases and wavelet ones, DeepGWC is constructed together with the reuse of residual connection and identity mappings in network architectures. Extensive experiments on three benchmark datasets including Cora, Citeseer, and Pubmed are conducted. The experimental results demonstrate that our DeepGWC outperforms existing graph deep models with the help of additional wavelet bases and achieves new state-of-the-art performances eventually.