AI Paper Atlas

Research map / Graph learning / GNN architectures

Conformal Prediction Sets for Graph Neural Networks

Soroush H. Zargarbashi, Simone Antonelli, Aleksandar Bojchevski

ICML 2023 · Graph learning › GNN architectures · approach: GNN generalization theory

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 1-hop neighborhood score diffusion (DAPS) to APS conformity scoresGCN on CoraML · CoraML transductiveefficiency (set size) and singleton hit ratio: Efficiency -0.50, singleton hit +0.09 vs APSImproved
Add score diffusion to APS (DAPS) on Coauthor CSGCN · Coauthor CS transductivesingleton hit ratio: +0.13 vs APSImproved
Use RAPS regularization instead of APSGCN on CoraML · CoraML transductivesingleton hit ratio: -0.22 vs APSHurt
Add score diffusion to APS on CoraML, plus higher-variance RAPS comparisonGCN · CoraML/PubMed/other small datasetsefficiency: RAPS efficiency ranges from +0.08 to -0.93 vs APS across datasetsMixed
Diffusion with lambda=0 vs tuned lambda (sweep) (ablation)GCN on CiteSeer · CiteSeeraccuracy: change negligibleNo clear effect
Use 2-hop diffusion or score propagation (SP) instead of 1-hop diffusion (ablation)GCN on CoraML · CoraMLefficiency and singleton hit ratio: both variants provide further improvements over 1-hop (qualitative)Improved
Add score diffusion to APS when only hard (one-hot) predictions are available (ablation)GCN on Coauthor-CS · hard predictionsefficiency and singleton hit ratio: APS fails catastrophically; DAPS remains reasonably close to soft baseline (qualitative)Improved
Add score diffusion on OGBN Arxiv (low homophily) (ablation)GCN · OGBN Arxivefficiency: diffusion does not provide a significant boost (qualitative)No clear effect
Replace NAPS with DAPS when many calibration nodes are unavailableGCN on CoraML · CoraML transductive, |Vc|=5.2%applicability and efficiency: NAPS N/A for 79% of nodes; DAPS 1.81 set size applicable to allImproved

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