AI Paper Atlas

Research map / Graph learning / GNN architectures

FairGSE: Fairness-Aware Graph Neural Network Without High False Positive Rates

Zhenqiang Ye, Jinjie Lu, Tianlong Gu, Fengrui Hao, Xuemin Wang

AAAI 2026 · Graph learning › GNN architectures · approach: Robustness, privacy, and fairness of GNNs · 3 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
add 2D structural entropy maximization with contrastive learning to a GCNVanilla GCN · CreditFPR (%): 45.96 -> 41.45Improved
add 2D structural entropy maximization with contrastive learning to a GCNVanilla GCN · CreditΔSP (%): 14.63 -> 5.09Improved
FairGSE versus FairSIN, which reaches near-zero ΔSP via a false-positive shortcutFairSIN · CreditFPR (%): 99.76 -> 41.45Improved
FairGSE versus FairSIN on group fairnessFairSIN · CreditΔSP (%): 0.52 -> 5.09Hurt
FairGSE versus second-best method on Pokec nFairGP · Pokec nFPR (%): 18.98 -> 18.46Improved
add graph structure learner (2D-SE maximization) on top of contrastive learning (ablation)FairGSE · CreditFPRImproved
add contrastive learning to 2D-SE structure learning (ablation)FairGSE · Credit, Pokec n, Pokec zAUC/FPR/fairnessImproved
add structure bootstrapping mechanism (ablation)FairGSE · Creditfairness (ΔSP, ΔEO)Improved
add structure bootstrapping mechanism (ablation)FairGSE · Pokec n, Pokec zoverall performanceNo clear effect
increase contrastive weight lambda1 beyond 0.5 (ablation)FairGSE · CreditFPRMixed
use smaller 2D-SE weight lambda2 (ablation)FairGSE · Creditfairness-FPR trade-offImproved

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