Joint Data Inpainting and Graph Learning via Unrolled Neural Networks
Not on the map. Why?
Abstract (arXiv)
Given partial measurements of a time-varying graph signal, we propose an algorithm to simultaneously estimate both the underlying graph topology and the missing measurements. The proposed algorithm operates by training an interpretable neural network, designed from the unrolling framework. The proposed technique can be used both as a graph learning and a graph signal reconstruction algorithm. This work enhances prior work in graph signal reconstruction by allowing the underlying graph to be unknown; and also builds on prior work in graph learning by tailoring the learned graph to the signal reconstruction task.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 21 of its 37 references that are in the map. First posted on arXiv 16 Jul 2024.
Builds on
21 of 37 references.
References · 21
- 2021Convex optimizationcited by 2,479
- 2019Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image Processingcited by 411
- 2017Graph Signal Processing: Overview, Challenges and Applicationscited by 409
- 2016How to learn a graph from smooth signalscited by 146
- 2019Stability Properties of Graph Neural Networkscited by 125
- 2018Learning graphs from data: A signal representation perspectivecited by 119
- 2018Connecting the Dots: Identifying Network Structure via Graph Signal Processingcited by 111
- 2018Convolutional Neural Network Architectures for Signals Supported on Graphscited by 94
- 2021Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Futurecited by 67
- 2016Learning heat diffusion graphscited by 39
- 2020Graph Unrolling Networks: Interpretable Neural Networks for Graph Signal Denoisingcited by 33
- 2014Signal Recovery on Graphs: Variation Minimizationcited by 26
9 more
- 2021Learning to Learn Graph Topologiescited by 26
- 2016Learning Sparse Graphs Under Smoothness Priorcited by 22
- 2015Sampling of graph signals with successive local aggregationscited by 19
- 2018Graph Learning from Filtered Signals: Graph System and Diffusion Kernel Identificationcited by 17
- 2020Time-Varying Graph Learning with Constraints on Graph Temporal Variationcited by 11
- 2017Filter Design for Autoregressive Moving Average Graph Filterscited by 8
- 2017Evaluating Graph Signal Processing for Neuroimaging Through Classification and Dimensionality Reductioncited by 7
- 2017Graph learning under sparsity priorscited by 4
- 2022Unrolled Graph Learning for Multi-Agent Collaborationcited by 1
Built on by
Not cited yet.