Graph Auto-encoder For Graph Signal Denoising

Signal denoising is an important problem with a vast literature. Recently, signal denoising on graphs has received a lot of attention due to the increasing use of graph-structured signals. However, well-etablished signal denoising methods do not generalize to graph signals with irregular structures, while existing graph denoising methods do not capture well the abstract representations inherent in the signals. To bridge this gap, we propose to use graph convolutional neural network with a Kron-reduction-based pooling operator for denoising on graphs. The proposed model can effectively capture the irregular data structure and learn the underlying representations in the signals, leading to improved performance over existing methods in experiments involving real-world traffic signals.

Publication year:2020

Keywords:graph signal denoising, graph autoencoders, graph neural networks, geometric deep learning

Accessibility:Closed