Salvato in:
Dettagli Bibliografici
Autori principali: Batreddy, Subbareddy, Mishra, Pushkal, Kakarla, Yaswanth, Siripuram, Aditya
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2407.11429
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917723179581440
author Batreddy, Subbareddy
Mishra, Pushkal
Kakarla, Yaswanth
Siripuram, Aditya
author_facet Batreddy, Subbareddy
Mishra, Pushkal
Kakarla, Yaswanth
Siripuram, Aditya
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2407_11429
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Joint Data Inpainting and Graph Learning via Unrolled Neural Networks
Batreddy, Subbareddy
Mishra, Pushkal
Kakarla, Yaswanth
Siripuram, Aditya
Signal Processing
Machine Learning
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.
title Joint Data Inpainting and Graph Learning via Unrolled Neural Networks
topic Signal Processing
Machine Learning
url https://arxiv.org/abs/2407.11429