AI Paper Atlas

Research map / Graph learning / GNN architectures

Quantile-Free Uncertainty Quantification in Graph Neural Networks

Soyoung Park, Hwanjun Song, Sungsu Lim

ICML 2026 · Graph learning › GNN architectures · approach: Robustness, privacy, and fairness of GNNs · 0 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 quantile-free joint loss instead of RQR loss (ablation)QpiGNN · BA (synthetic)PICP: 0.19 -> 0.98Improved
use quantile-free joint loss instead of RQR loss (ablation)QpiGNN · Tree (synthetic)PICP: 0.27 -> 0.96Improved
use quantile-free joint loss instead of RQR loss (ablation)QpiGNN · ChameleonMPIW: 0.30 -> 0.23Improved
lower width penalty lambda from 0.5 to 0.1QpiGNN · BA (synthetic)MPIW: 0.49 -> 1.01Hurt
use Bayesian-optimized lambda instead of 0.5QpiGNN · ChameleonPICP: 0.51 -> 0.96Improved
use Bayesian-optimized lambda instead of 0.5QpiGNN · TwitchPICP: 0.59 -> 0.94Improved
add dual-head architecture with learnable margin (ablation)QpiGNN · nine synthetic datasetsPICP-MPIW trade-offImproved
add coverage and width terms jointly in loss (ablation)QpiGNN · nine synthetic datasetsPICP-MPIW trade-offImproved
increase edge dropout from 0.2 to 0.6QpiGNN · ER graphsPICP: 0.84 -> 0.91Improved
increase target noise sigma from 0.1 to 0.3QpiGNN · ER graphsMPIW: 0.44 -> 1.05Hurt
use community split instead of random splitQpiGNN · EducationMPIW: 0.90 -> 0.54Improved
use degree split instead of random splitQpiGNN · TwitchMPIW: 0.54 -> 0.68Hurt

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