AI Paper Atlas

Research map / Graph learning / GNN architectures

Graph Neural Networks with Convolutional ARMA Filters

Filippo Maria Bianchi, Daniele Grattarola, Lorenzo Livi, Cesare Alippi

TPAMI 2021 · Graph learning › GNN architectures · approach: Deep graph convolution and simplification · 479 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use ARMA layer instead of GCN layerGNN · PPIaccuracy: 80.8 -> 90.5Improved
use ARMA layer instead of Chebyshev layerGNN · PPIaccuracy: 86.4 -> 90.5Improved
use ARMA layer instead of GCN layerGNN · Coraaccuracy: 81.5 -> 83.4Improved
use ARMA layer instead of CayleyNetGNN · Citeseeraccuracy: 67.1 -> 72.5Improved
use ARMA layer instead of GCN layerGNN · Pubmedaccuracy: 79.0 -> 78.9No clear effect
use ARMA layer instead of GCN layerGNN · 20newsaccuracy: 65.45 -> 70.02Improved
use ARMA layer instead of GCN layerGNN · MNISTaccuracy: 98.48 -> 99.20Improved
use ARMA layer instead of Chebyshev layerGNN · MNISTaccuracy: 99.14 -> 99.20No clear effect
use ARMA layer instead of GCN layerGNN · D&Daccuracy: 74.7 -> 77.6Improved
use ARMA layer instead of CayleyNetGNN · MUTAGaccuracy: 87.8 -> 91.5Improved
use ARMA layer instead of Chebyshev layerGNN · Enzymesaccuracy: 57.9 -> 60.6Improved
use ARMA layer instead of CayleyNetGNN · QM9 U0_atomMSE: 1.493 -> 0.053Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy