AI Paper Atlas

Research map / Graph learning / GNN architectures

GStarX: Explaining Graph Neural Networks with Structure-Aware Cooperative Games

Shichang Zhang, Yozen Liu, Neil Shah, Yizhou Sun

NeurIPS 2022 · Graph learning › GNN architectures · approach: GNN explainability · 10 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
Use structure-aware HN-value scoring instead of SubgraphX's Shapley-based explanation scoringGCN explanation · BA2MotifsH-Fidelity: 0.6050 -> 0.5824Hurt
Use structure-aware HN-value scoring instead of Shapley-based explanation scoringGCN explanation · BACEH-Fidelity: 0.5519 -> 0.5934Improved
Use structure-aware HN-value scoring instead of Shapley-based explanation scoringGCN explanation · BBBPH-Fidelity: 0.5610 -> 0.5227Hurt
Use structure-aware HN-value scoring instead of Shapley-based explanation scoringGCN explanation · GraphSST2H-Fidelity: 0.5487 -> 0.5519Improved
Use structure-aware HN-value scoring instead of Shapley-based explanation scoringGCN explanation · MUTAGH-Fidelity: 0.5253 -> 0.6171Improved
Use structure-aware HN-value scoring instead of Shapley-based explanation scoringGCN explanation · TwitterH-Fidelity: 0.5494 -> 0.5716Improved
Use HN-value scoring rather than the strongest baselineGAT explanation · GraphSST2H-Fidelity: 0.5484 -> 0.5542Improved
Use HN-value scoring rather than the strongest baselineGIN explanation · MUTAGH-Fidelity: 0.5592 -> 0.6064Improved
Use GStarX rather than SubgraphXGCN explanation · BBBPTime(s): 75.96 -> 31.24Improved

Later papers that compared with this method

1 later accepted paper reports GStarX as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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