Adaptive Least Mean Squares Graph Neural Networks and Online Graph Signal Estimation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yan, Yi, Peng, Changran, Kuruoglu, Ercan Engin
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911766710059008
author Yan, Yi
Peng, Changran
Kuruoglu, Ercan Engin
author_facet Yan, Yi
Peng, Changran
Kuruoglu, Ercan Engin
contents The online prediction of multivariate signals, existing simultaneously in space and time, from noisy partial observations is a fundamental task in numerous applications. We propose an efficient Neural Network architecture for the online estimation of time-varying graph signals named the Adaptive Least Mean Squares Graph Neural Networks (LMS-GNN). LMS-GNN aims to capture the time variation and bridge the cross-space-time interactions under the condition that signals are corrupted by noise and missing values. The LMS-GNN is a combination of adaptive graph filters and Graph Neural Networks (GNN). At each time step, the forward propagation of LMS-GNN is similar to adaptive graph filters where the output is based on the error between the observation and the prediction similar to GNN. The filter coefficients are updated via backpropagation as in GNN. Experimenting on real-world temperature data reveals that our LMS-GNN achieves more accurate online predictions compared to graph-based methods like adaptive graph filters and graph convolutional neural networks.
format Preprint
id arxiv_https___arxiv_org_abs_2401_15304
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Adaptive Least Mean Squares Graph Neural Networks and Online Graph Signal Estimation
Yan, Yi
Peng, Changran
Kuruoglu, Ercan Engin
Machine Learning
Signal Processing
The online prediction of multivariate signals, existing simultaneously in space and time, from noisy partial observations is a fundamental task in numerous applications. We propose an efficient Neural Network architecture for the online estimation of time-varying graph signals named the Adaptive Least Mean Squares Graph Neural Networks (LMS-GNN). LMS-GNN aims to capture the time variation and bridge the cross-space-time interactions under the condition that signals are corrupted by noise and missing values. The LMS-GNN is a combination of adaptive graph filters and Graph Neural Networks (GNN). At each time step, the forward propagation of LMS-GNN is similar to adaptive graph filters where the output is based on the error between the observation and the prediction similar to GNN. The filter coefficients are updated via backpropagation as in GNN. Experimenting on real-world temperature data reveals that our LMS-GNN achieves more accurate online predictions compared to graph-based methods like adaptive graph filters and graph convolutional neural networks.
title Adaptive Least Mean Squares Graph Neural Networks and Online Graph Signal Estimation
topic Machine Learning
Signal Processing
url https://arxiv.org/abs/2401.15304