Graph Signal Restoration Using Nested Deep Algorithm Unrolling
Open Access
- 14 June 2022
- journal article
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal Processing
- Vol. 70 (1053587X) , 3296-3311
Abstract
Graph signal processing is a ubiquitous task in many applications such as sensor, social, transportation and brain networks, point cloud processing, and graph neural networks. Often, graph signals are corrupted in the sensing process, thus requiring restoration. In this paper, we propose two graph signal restoration methods based on deep algorithm unrolling (DAU). First, we present a graph signal denoiser by unrolling iterations of the alternating direction method of multiplier (ADMM). We then suggest a general restoration method for linear degradation by unrolling iterations of Plug-and-Play ADMM (PnP-ADMM). In the second approach, the unrolled ADMM-based denoiser is incorporated as a submodule, leading to a nested DAU structure. The parameters in the proposed denoising/restoration methods are trainable in an end-to-end manner. Our approach is interpretable and keeps the number of parameters small since we only tune graph-independent regularization parameters. We overcome two main challenges in existing graph signal restoration methods: 1) limited performance of convex optimization algorithms due to fixed parameters which are often determined manually. 2) large number of parameters of graph neural networks that result in difficulty of training. Several experiments for graph signal denoising and interpolation are performed on synthetic and real-world data. The proposed methods show performance improvements over several existing techniques in terms of root mean squared error in both tasks.Keywords
All Related Versions
Funding Information
- JST PRESTO (JPMJPR1935)
- JSPS KAKENHI (20H02145)
- US National Science Foundation (1763896, 2030570, 2134209, 2133032)
This publication has 48 references indexed in Scilit:
- Signal Recovery on Graphs: Variation MinimizationIEEE Transactions on Signal Processing, 2015
- Total generalized variation for graph signals2015
- Multiresolution Graph Fourier Transform for Compression of Piecewise Smooth ImagesIEEE Transactions on Image Processing, 2014
- $M$ -Channel Oversampled Graph Filter BanksIEEE Transactions on Signal Processing, 2014
- Proximal AlgorithmsFoundations and Trends® in Optimization, 2014
- Distributed Optimization and Statistical Learning via the Alternating Direction Method of MultipliersFoundations and Trends in Machine Learning, 2011
- Graph spectral image smoothing using the heat kernelPattern Recognition, 2008
- A New Alternating Minimization Algorithm for Total Variation Image ReconstructionSIAM Journal on Imaging Sciences, 2008
- Regularization and Variable Selection Via the Elastic NetJournal of the Royal Statistical Society Series B: Statistical Methodology, 2005
- The digital TV filter and nonlinear denoisingIEEE Transactions on Image Processing, 2001