AI Paper Atlas

Research map / Graph learning / GNN architectures

How Powerful are Spectral Graph Neural Networks

Xiyuan Wang, Muhan Zhang

ICML 2022 · Graph learning › GNN architectures · approach: Subgraph and distance-aware GNNs · 36 citations (OpenAlex)

Read the paper

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
remove nonlinearity: use linear spectral GNN with Jacobi basis (JacobiConv) instead of nonlinear spectral GNNsspectral GNNs on real-world node classification · 10 real-world datasets (Table 2)accuracy (%): up to 12% gain on Squirrel; best on 9 of 10 datasetsImproved
add nonlinearity via 2-layer ReLU MLP in place of linear transform (ablation)JacobiConv · Cora, Computers, Photo, Squirrel etc. (Table 3)accuracy (%): about 6% average loss vs JacobiConvHurt
use Jacobi basis instead of monomial/Chebyshev/Bernstein bases in linear GNN (ablation)linear spectral GNN · real-world datasets (Table 3)accuracy (%): more than 0.8% average over other basesImproved
use multiple per-output-dimension filter functions instead of one shared filter (ablation)JacobiConv · real-world datasets (Table 3)accuracy (%): about 1.3% average gainImproved
add polynomial coefficient decomposition (PCD) (ablation)JacobiConv · real-world datasets (Table 3)accuracy (%): about 0.8% average gainImproved
replace node features with random features (no learnable random features) (ablation)JacobiConv · real-world datasets (Table 4)accuracy (%): Cora 88.98 to 23.46Hurt
Jacobi basis vs Bernstein basis in linear filters on synthetic image filter learning (ablation)linear GNN · synthetic image filter learning (Table 1)average squared loss: Jacobi 0.0003 vs Bernstein 0.0110 on Low filterImproved

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