Graph Neural Networks With Convolutional ARMA Filters

Popular graph neural networks implement convolution operations on graphs based on polynomial spectral filters. In this paper, we propose a novel graph convolutional layer inspired by the auto-regressive moving average (ARMA) filter that, compared to polynomial ones, provides a more flexible frequenc...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on pattern analysis and machine intelligence 2022-07, Vol.44 (7), p.3496-3507
Hauptverfasser:	Bianchi, Filippo Maria, Grattarola, Daniele, Livi, Lorenzo, Alippi, Cesare
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Autoregressive moving average Chebyshev approximation Convolution Downstream effects Eigenvalues and eigenfunctions Frequency response Geometric deep learning graph filters Graph neural networks graph signal processing graph theory Graphs Laplace equations Neural Networks, Computer Polynomials Signal classification Spectrum analysis Task analysis
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!