Understanding Graph Neural Networks from Graph Signal Denoising Perspectives

by   Guoji Fu, et al.

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 <https://github.com/fuguoji/GSDN>.


page 5

page 9


On Positional and Structural Node Features for Graph Neural Networks on Non-attributed Graphs

Graph neural networks (GNNs) have been widely used in various graph-rela...

How Powerful is Implicit Denoising in Graph Neural Networks

Graph Neural Networks (GNNs), which aggregate features from neighbors, a...

Spectral Heterogeneous Graph Convolutions via Positive Noncommutative Polynomials

Heterogeneous Graph Neural Networks (HGNNs) have gained significant popu...

Large-scale graph representation learning with very deep GNNs and self-supervision

Effectively and efficiently deploying graph neural networks (GNNs) at sc...

Fisher Information Embedding for Node and Graph Learning

Attention-based graph neural networks (GNNs), such as graph attention ne...

Graphtester: Exploring Theoretical Boundaries of GNNs on Graph Datasets

Graph Neural Networks (GNNs) have emerged as a powerful tool for learnin...

Spectral Graph Attention Network

Variants of Graph Neural Networks (GNNs) for representation learning hav...

Code Repositories


The source code of the paper "Understanding Graph Neural Networks from Graph Signal Denoising Perspectives"

view repo

Please sign up or login with your details

Forgot password? Click here to reset