AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

D4Explainer: In-distribution Explanations of Graph Neural Network via Discrete Denoising Diffusion

Jialin Chen, Shirley Wu, Abhijit Gupta, Zhitao Ying

NeurIPS 2023 · Graph learning › Graph self-supervised learning · approach: Diffusion-based graph generation · 8 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
reduce reverse sampling steps T from 50 to 10 (K=20) (ablation)D4Explainer · Mutag model-leveltarget class probability: 0.812 -> 0.524Hurt
increase T from 50 to 100 (K=20) (ablation)D4Explainer · Mutag model-leveltarget class probability: 0.812 -> 0.832Improved
reduce candidates K from 20 to 10 (T=50) (ablation)D4Explainer · Mutag model-leveltarget class probability: 0.812 -> 0.799Hurt
increase K from 20 to 30 (T=50) (ablation)D4Explainer · Mutag model-leveltarget class probability: 0.812 -> 0.823Improved
vary K and T on Tree-Cycle (ablation)D4Explainer · Tree-Cycle model-leveltarget class probability: 0.987 -> 0.997No clear effect
D4Explainer vs CF-GNNExplainer on counterfactual accuracyD4Explainer · CornellCF-ACC AUC: 0.328 -> 0.623Improved
D4Explainer vs CF-GNNExplainer on BA-3MotifD4Explainer · BA-3MotifCF-ACC AUC: 0.302 -> 0.912Improved
D4Explainer vs CF-GNNExplainer on NCI1 (only small gap)D4Explainer · NCI1CF-ACC AUC: 0.715 -> 0.737Improved
D4Explainer vs CF-GNNExplainer on MutagD4Explainer · MutagCF-ACC AUC: 0.797 -> 0.765No clear effect
D4Explainer vs CF-GNNExplainer MMD sumD4Explainer · BBBPMMD Sum: 0.1264 -> 0.0861Improved
D4Explainer vs XGNN sparsityD4Explainer · Mutag model-leveldensity: 0.537 -> 0.278Improved
D4Explainer vs XGNN with 5 nodes on Tree-CycleD4Explainer · Tree-Cycle model-leveltarget class probability: 0.968 -> 0.991No clear effect

Later papers that compared with this method

2 later accepted papers report D4Explainer as a baseline in their results tables; 2 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