AI Paper Atlas

Research map / Graph learning / GNN architectures

Learning Fair Graph Representations via Probability of Necessity and Sufficiency

Chuxun Liu, Qingfeng Chen, Debo Cheng, Jiangzhang Gan, Jiuyong Li, Lin Liu

AAAI 2026 · Graph learning › GNN architectures · approach: Graph structure learning · 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 necessity and sufficiency (PNS) constraints on top of the discriminator (ablation)FairSNR · ablation datasets (Figure 4)F1 and DP trade-offImproved
add the adversarial discriminator (ablation)FairSNR · ablation datasets (Figure 4)F1 and DP trade-offImproved
remove necessity/sufficiency constraints (adversarial learning only) (ablation)FairSNR · ablation datasets (Figure 4)predictive performanceHurt
set adversarial strength beta to 0.01 (moderate) (ablation)FairSNR · Credit and Pokec-zfairness and utilityImproved
too small or too large KL weight alpha (ablation)FairSNR · Credit and Pokec-zfairness and utilityHurt
FairSNR versus vanilla GCN on small datasetsFairSNR · GermanAUC: 73.49 -> 66.17Hurt
FairSNR versus vanilla GCN on fairnessGCN · GermanDP: 33.75 -> 0.64Improved

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