AI Paper Atlas

Research map / Graph learning / GNN architectures

DeloopSGNN: Revisiting Spectral GNNs Through the Lens of Spatial Aggregation

Duanyu Li, Huijun Wu, Min Xie, Kai Lu, Wenzhe Zhang, Zhenwei Wu, Yong Dong, Ruibo Wang

AAAI 2026 · Graph learning › GNN architectures · approach: Spectral GNN design · 0 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
replace A^k aggregation with acyclic-path aggregation (DeloopSGNN) vs BernNetspectral GNN · Squirrelaccuracy: 48.3 ± 1.2 -> 56.4 ± 1.4Improved
use DeloopSGNN vs JacobiConvspectral GNN · Squirrelaccuracy: 54.6 ± 1.6 -> 56.4 ± 1.4Improved
use DeloopSGNN vs GCNspatial GNN · Squirrelaccuracy: 46.9 ± 0.6 -> 56.4 ± 1.4Improved
use DeloopSGNN vs GPRGNNspectral GNN · Chameleonaccuracy: 52.9 ± 1.1 -> 69.3 ± 0.9Improved
use DeloopSGNN vs BernNet under Metattack 10% vs clean on Photorobustness · Photoaccuracy: 94.8 ± 0.1 -> 92.9 ± 0.7Improved
use acyclic path constraint under strong Metattack 15%DeloopSGNN vs GCN · Photo (Metattack 15%)accuracy: 76.3 ± 2.7 -> 89.1 ± 1.8Improved
use acyclic path constraint under strong Metattack 15%DeloopSGNN vs GCNSVD · Citeseer (Metattack 15%)accuracy: 65.6 ± 1.4 -> 64.1 ± 1.1Hurt
use acyclic path constraint under PGD 15%DeloopSGNN vs best baseline · Computers (PGD 15%)accuracy: 73.2 ± 5.4 -> 79.0 ± 0.8Improved
use DeloopSGNN on clean graphs vs GCN-SVDGCNSVD · Computers (clean)accuracy: 77.0 ± 1.7 -> 90.7 ± 0.4Improved
use DeloopSGNN vs EvenNetspectral GNN · Texasaccuracy: 93.8 ± 1.8 -> 93.0 ± 0.8No clear effect
use DeloopSGNN vs H2GCNspatial GNN · Reed98accuracy: 69.2 ± 2.3 -> 75.1 ± 2.9Improved
use DeloopSGNN vs GATspatial GNN · Reed98accuracy: 76.8 ± 0.5 -> 75.1 ± 2.9No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 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