Graph Unrolling Networks: Interpretable Neural Networks for Graph Signal Denoising

TL;DR

This paper introduces graph unrolling networks, a novel interpretable neural network framework for denoising graph signals that combines algorithm unrolling with graph signal processing insights.

Contribution

It develops a new graph neural network architecture based on unrolling iterative denoising algorithms, with adaptive edge-weight sharing and unsupervised training, enhancing interpretability and performance.

Findings

Achieves 40-60% lower denoising error than traditional methods.

Demonstrates superior performance over state-of-the-art graph neural networks.

Provides an interpretable framework linking neural networks and signal processing.

Abstract

We propose an interpretable graph neural network framework to denoise single or multiple noisy graph signals. The proposed graph unrolling networks expand algorithm unrolling to the graph domain and provide an interpretation of the architecture design from a signal processing perspective. We unroll an iterative denoising algorithm by mapping each iteration into a single network layer where the feed-forward process is equivalent to iteratively denoising graph signals. We train the graph unrolling networks through unsupervised learning, where the input noisy graph signals are used to supervise the networks. By leveraging the learning ability of neural networks, we adaptively capture appropriate priors from input noisy graph signals, instead of manually choosing signal priors. A core component of graph unrolling networks is the edge-weight-sharing graph convolution operation, which parameterizes each edge weight by a trainable kernel function where the trainable parameters are shared by all the edges. The proposed convolution is permutation-equivariant and can flexibly adjust the edge weights to various graph signals. We then consider two special cases of this class of networks, graph unrolling sparse coding (GUSC) and graph unrolling trend filtering (GUTF), by unrolling sparse coding and trend filtering, respectively. To validate the proposed methods, we conduct extensive experiments on both real-world datasets and simulated datasets, and demonstrate that our methods have smaller denoising errors than conventional denoising algorithms and state-of-the-art graph neural networks. For denoising a single smooth graph signal, the normalized mean square error of the proposed networks is around 40% and 60% lower than that of graph Laplacian denoising and graph wavelets, respectively.