AI Paper Atlas

Research map / Graph learning / GNN architectures

Multi-scale Explainer for Graph Neural Networks

Lutong Wu, Shiying Cheng, Zhiqiang Wang, Jianqing Liang, Peng Song, Xizhao Luo, Jiye Liang

ICML 2026 · Graph learning › GNN architectures · approach: GNN explainability

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 multi-scale consistency guidance (ablation)MSExplainer · six benchmarks, edge ratio 0.7prediction accuracyImproved
add single-scale adaptive (contrastive) learning (ablation)MSExplainer · six benchmarks, edge ratio 0.7prediction accuracyImproved
use multiple scales (M=9) instead of single scale (M=1) (ablation)MSExplainer · Mutagenicityprediction accuracyImproved
increase number of scales beyond M=9 (ablation)MSExplainer · Mutagenicityprediction accuracyNo clear effect
set loss ratio lambda1/lambda2 within 1 to 10 instead of 0.01 or 100 (ablation)MSExplainer · prediction accuracy over scalesprediction accuracyImproved
use MSExplainer instead of GSCExplainerMSExplainer · Mutagenicity (edge ratio 0.9)prediction accuracy (%): 87.2 -> 100.0Improved
use MSExplainer instead of OrphicXMSExplainer · BA-2Motif (edge ratio 0.5)prediction accuracy (%): 78.0 -> 84.0Improved
use MSExplainer instead of MixupExplainerMSExplainer · NCI1 (edge ratio 0.5)prediction accuracy (%): 72.5 -> 70.8Hurt
use MSExplainer instead of GSCExplainerMSExplainer · MutagenicityEdge AUC (%): 91.3 -> 93.0Improved
use parameter sharing across scalesMSExplainer · training costcomputational complexityNo clear effect

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