AI Paper Atlas

Research map / Graph learning / GNN architectures

SAME: Uncovering GNN Black Box with Structure-aware Shapley-based Multipiece Explanations

Ziyuan Ye, Rihan Huang, Qilin Wu, Quanying Liu

NeurIPS 2023 · Graph learning › GNN architectures · approach: GNN explainability · 2 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
SAME vs previous SOTA explainerSAME · BBBPfidelity: 0.433 -> 0.489Improved
SAME vs previous SOTA explainerSAME · MUTAGfidelity: 0.656 -> 0.702Improved
SAME vs previous SOTA explainerSAME · Graph-SST2fidelity: 0.262 -> 0.373Improved
SAME vs previous SOTA explainerSAME · Graph-SST5fidelity: 0.283 -> 0.393Improved
SAME vs previous SOTA explainerSAME · BA-2Motifsfidelity: 0.493 -> 0.549Improved
SAME vs previous SOTA explainerSAME · BA-Shapesfidelity: 0.181 -> 0.214Improved
SAME vs previous SOTA on harmonic fidelitySAME · graph classification datasetsharmonic fidelity: 1.92%Improved
SAME vs SOTA on inverse fidelitySAME · 6 datasetsinverse fidelityMixed
SAME vs SubgraphX on costSAME · BBBPinference time (s): 26.72 -> 7.86Improved
SAME vs GStarX on costSAME · BBBPinference time (s): 84.54 -> 7.86Improved
Increase K from 1 to 9 at gamma=1 (ablation)SAME · Graph-SST5 (30 graphs)fidelity: 0.2511 -> 0.4026Improved
Increase gamma from 1 to 5 at K=7 (ablation)SAME · Graph-SST5 (30 graphs)fidelity: 0.3938 -> 0.3591Hurt

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