Understanding Graph Neural Networks from Graph Signal Denoising Perspectives
arXiv:2006.04386
Abstract
Graph neural networks (GNNs) have attracted much attention because of their excellent performance on tasks such as node classification. However, there is inadequate understanding on how and why GNNs work, especially for node representation learning. This paper aims to provide a theoretical framework to understand GNNs, specifically, spectral graph convolutional networks and graph attention networks, from graph signal denoising perspectives. Our framework shows that GNNs are implicitly solving graph signal denoising problems: spectral graph convolutions work as denoising node features, while graph attentions work as denoising edge weights. We also show that a linear self-attention mechanism is able to compete with the state-of-the-art graph attention methods. Our theoretical results further lead to two new models, GSDN-F and GSDN-EF, which work effectively for graphs with noisy node features and/or noisy edges. We validate our theoretical findings and also the effectiveness of our new models by experiments on benchmark datasets. The source code is available at \url{https://github.com/fuguoji/GSDN}.
19 pages, 8 figures
References in corpus (7)
- Semi-Supervised Classification with Graph Convolutional Networks
- Discrete Signal Processing on Graphs
- Deep Convolutional Networks on Graph-Structured Data
- Fast Graph Representation Learning with PyTorch Geometric
- Simplifying Graph Convolutional Networks
- Predicting multicellular function through multi-layer tissue networks
- Revisiting Graph Neural Networks: All We Have is Low-Pass Filters