Autoregressive Moving Average Graph Filtering

DOI10.1109/TSP.2016.2614793zbMATH Open1414.94270arXiv1602.04436OpenAlexW2521050763MaRDI QIDQ4620535FDOQ4620535

Authors: Elvin Isufi, Andreas Loukas, Andrea Simonetto, G. Leus 

Publication date: 8 February 2019

Published in: IEEE Transactions on Signal Processing (Search for Journal in Brave)

Abstract: One of the cornerstones of the field of signal processing on graphs are graph filters, direct analogues of classical filters, but intended for signals defined on graphs. This work brings forth new insights on the distributed graph filtering problem. We design a family of autoregressive moving average (ARMA) recursions, which (i) are able to approximate any desired graph frequency response, and (ii) give exact solutions for tasks such as graph signal denoising and interpolation. The design philosophy, which allows us to design the ARMA coefficients independently from the underlying graph, renders the ARMA graph filters suitable in static and, particularly, time-varying settings. The latter occur when the graph signal and/or graph are changing over time. We show that in case of a time-varying graph signal our approach extends naturally to a two-dimensional filter, operating concurrently in the graph and regular time domains. We also derive sufficient conditions for filter stability when the graph and signal are time-varying. The analytical and numerical results presented in this paper illustrate that ARMA graph filters are practically appealing for static and time-varying settings, as predicted by theoretical derivations.

Full work available at URL: https://arxiv.org/abs/1602.04436

Mathematics Subject Classification ID

Signal theory (characterization, reconstruction, filtering, etc.) (94A12)

Cited In (13)

• Bayesian reconstruction of Cartesian product graph signals with general patterns of missing data
• Distributed reconstruction of time-varying graph signals via a modified Newton's method
• Universal graph filter design based on Butterworth, Chebyshev, and elliptic functions
• Approximating spectral clustering via sampling: a review
• Title not available (Why is that?)
• Generalizing Graph Signal Processing: High Dimensional Spaces, Models and Structures
• Polynomial graph filters of multiple shifts and distributed implementation of inverse filtering
• The dual graph shift operator: identifying the support of the frequency domain
• BiGCN: A bi-directional low-pass filtering graph neural network
• Unscented Kalman filter of graph signals
• \(\mathcal{L}_p\)-norm of the LMS algorithm for bilinear forms with \(\alpha\)-stable processes
• Spectral Laplace transform of signals on arbitrary domains
• Complex exponential graph convolutional networks

This page was built for publication: Autoregressive Moving Average Graph Filtering

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4620535)