Bayesian Convolutional Neural Networks for Prior Learning in Graph Signal Recovery

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Torkamani, Razieh, Amini, Arash, Zayyani, Hadi, Korki, Mehdi
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915509309538304
author Torkamani, Razieh
Amini, Arash
Zayyani, Hadi
Korki, Mehdi
author_facet Torkamani, Razieh
Amini, Arash
Zayyani, Hadi
Korki, Mehdi
contents Graph signal recovery (GSR) is a fundamental problem in graph signal processing, where the goal is to reconstruct a complete signal defined over a graph from a subset of noisy or missing observations. A central challenge in GSR is that the underlying statistical model of the graph signal is often unknown or too complex to specify analytically. To address this, we propose a flexible, data-driven framework that learns the signal prior directly from training samples. We develop a Bayesian convolutional neural network (BCNN) architecture that models the prior distribution of graph signals using graph-aware filters based on Chebyshev polynomials. By interpreting the hidden layers of the CNN as Gibbs distributions and employing Gaussian mixture model (GMM) nonlinearities, we obtain a closed-form and expressive prior. This prior is integrated into a variational Bayesian (VB) inference framework to estimate the posterior distribution of the signal and noise precision. Extensive experiments on synthetic and real-world graph datasets demonstrate that the proposed BCNN-GSR algorithm achieves accurate and robust recovery across a variety of signal distributions. The method generalizes well to complex, non-Gaussian signal models and remains computationally efficient, making it suitable for practical large-scale graph recovery tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2509_19056
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Bayesian Convolutional Neural Networks for Prior Learning in Graph Signal Recovery
Torkamani, Razieh
Amini, Arash
Zayyani, Hadi
Korki, Mehdi
Signal Processing
Graph signal recovery (GSR) is a fundamental problem in graph signal processing, where the goal is to reconstruct a complete signal defined over a graph from a subset of noisy or missing observations. A central challenge in GSR is that the underlying statistical model of the graph signal is often unknown or too complex to specify analytically. To address this, we propose a flexible, data-driven framework that learns the signal prior directly from training samples. We develop a Bayesian convolutional neural network (BCNN) architecture that models the prior distribution of graph signals using graph-aware filters based on Chebyshev polynomials. By interpreting the hidden layers of the CNN as Gibbs distributions and employing Gaussian mixture model (GMM) nonlinearities, we obtain a closed-form and expressive prior. This prior is integrated into a variational Bayesian (VB) inference framework to estimate the posterior distribution of the signal and noise precision. Extensive experiments on synthetic and real-world graph datasets demonstrate that the proposed BCNN-GSR algorithm achieves accurate and robust recovery across a variety of signal distributions. The method generalizes well to complex, non-Gaussian signal models and remains computationally efficient, making it suitable for practical large-scale graph recovery tasks.
title Bayesian Convolutional Neural Networks for Prior Learning in Graph Signal Recovery
topic Signal Processing
url https://arxiv.org/abs/2509.19056