Graph Unrolling Networks: Interpretable Neural Networks for Graph Signal Denoising

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.

References in corpus (23)

• DeepWalk: Online Learning of Social Representations
• The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains
• Neural Message Passing for Quantum Chemistry
• Geometric deep learning: going beyond Euclidean data
• Spectral Networks and Locally Connected Networks on Graphs
• Discrete Signal Processing on Graphs
• Simplifying Graph Convolutional Networks
• Deep Image Prior
• Discrete Signal Processing on Graphs: Sampling Theory
• Learning graphs from data: A signal representation perspective
• Perfect Reconstruction Two-Channel Wavelet Filter-Banks for Graph Structured Data
• Efficient Sampling Set Selection for Bandlimited Graph Signals Using Graph Spectral Proxies
• Convolutional Neural Network Architectures for Signals Supported on Graphs
• Signal Recovery on Graphs: Variation Minimization
• Real-time Power System State Estimation and Forecasting via Deep Neural Networks
• PairNorm: Tackling Oversmoothing in GNNs
• Learning ReLU Networks on Linearly Separable Data: Algorithm, Optimality, and Generalization
• Subgraph-based filterbanks for graph signals
• Two-Channel Critically-Sampled Graph Filter Banks With Spectral Domain Sampling
• Learned SPARCOM: Unfolded Deep Super-Resolution Microscopy
• Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image Processing
• Vector-Valued Graph Trend Filtering with Non-Convex Penalties
• Detecting Localized Categorical Attributes on Graphs

Cited by in corpus (8)

• Graph-based Algorithm Unfolding for Energy-aware Power Allocation in Wireless Networks
• Graph Signal Restoration Using Nested Deep Algorithm Unrolling
• Joint Time-Vertex Fractional Fourier Transform
• A Review of Graph-Powered Data Quality Applications for IoT Monitoring Sensor Networks
• Dual Geometric Graph Network (DG2N) -- Iterative network for deformable shape alignment
• DPC: Unsupervised Deep Point Correspondence via Cross and Self Construction
• Graph Denoising with Framelet Regularizer
• Untrained Graph Neural Networks for Denoising