AI Paper Atlas

Research map / Graph learning / GNN architectures

Node-Oriented Spectral Filtering for Graph Neural Networks

Shuai Zheng, Zhenfeng Zhu, Zhizhe Liu, Youru Li, Yao Zhao

TPAMI 2023 · Graph learning › GNN architectures · approach: Spectral GNN design · 37 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
add node-oriented filtering (ablation)Chebyshev-basis spectral GNN · Coraaccuracy (%): 76.07 -> 77.69Improved
add node-oriented filtering (ablation)Chebyshev-basis spectral GNN · Citeseeraccuracy (%): 65.11 -> 67.74Improved
add node-oriented filtering (ablation)Chebyshev-basis spectral GNN · Pubmedaccuracy (%): 84.02 -> 85.07Improved
add node-oriented filtering (ablation)Chebyshev-basis spectral GNN · Chameleonaccuracy (%): 68.48 -> 72.52Improved
add node-oriented filtering (ablation)Chebyshev-basis spectral GNN · Actoraccuracy (%): 39.11 -> 40.62Improved
add node-oriented filtering (ablation)Chebyshev-basis spectral GNN · Texasaccuracy (%): 92.47 -> 94.03Improved
add node-oriented filtering (ablation)Monomial-basis spectral GNN · Texasaccuracy (%): 91.80 -> 91.47Hurt
add node-oriented filtering (ablation)Monomial-basis spectral GNN · Pubmedaccuracy (%): 82.28 -> 84.79Improved
add node-oriented filtering (ablation)Bernstein-basis spectral GNN · Chameleonaccuracy (%): 67.82 -> 69.93Improved
increase polynomial order K from 1 to 3 (ablation)NFGNN · several datasetsaccuracyImproved
increase low-rank order d from 1 to 5 (ablation)NFGNN · several datasetsaccuracyNo clear effect
use node-oriented filter instead of global filters (GPRGNN, BernNet)NFGNN · Chameleon (full-supervised)accuracy (%): 67.48 -> 72.52Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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