AI Paper Atlas

Research map / Probabilistic and scientific modeling / Causal discovery

Counterfactual Fairness with Imperfect Causal Graphs

Cong Su, Qiaoyu Tan, Carlotta Domeniconi, Lizhen Cui, Jun Wang, Guoxian Yu

AAAI 2026 · Probabilistic and scientific modeling › Causal discovery · approach: Causal approaches to fairness · 1 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
bound counterfactual quantities using local possible-descendant sets (CF-ICG) instead of using only definite non-descendants (Fair)counterfactually fair classifier · Synthetic (20 nodes, 40 edges)accuracy: 0.795 -> 0.835Improved
use CF-ICG instead of IFair for unidentifiable counterfactual quantitiescounterfactually fair classifier · Synthetic (20 nodes, 40 edges)unfairness: 0.136 -> 0.044Improved
apply CF-ICG fairness reconstruction on top of unconstrained baseline2-layer MLP · Adultunfairness: 0.193 -> 0.043Improved
apply CF-ICG fairness reconstruction on top of unconstrained baseline2-layer MLP · Adultaccuracy: 0.787 -> 0.753Hurt
apply CF-ICG fairness reconstruction on top of unconstrained baseline2-layer MLP · Compasunfairness: 0.232 -> 0.048Improved
apply CF-ICG fairness reconstruction on top of unconstrained baseline2-layer MLP · ACSPublicCoverageunfairness: 0.247 -> 0.037Improved
use local structure of CF-ICG with different causal discovery algorithms (true CPDAG, PC, GES, MB-by-MB) (ablation)CF-ICG · Synthetic (20 and 40 nodes)accuracy and unfairnessNo clear effect
increase CPDAG error rate from 0.2 to 0.6 (ablation)CF-ICG vs IFair and Fair · Synthetic (20 nodes, 40 edges)accuracy and unfairnessMixed
use CF-ICG bounds on counterfactual fairness under unidentifiable contextsCF-ICG · Synthetic (20 nodes, 40 edges)bound coverage of ground truth: truth 0.186 within [0.173, 0.446]Improved
exclude the sensitive attribute only (Unaware) rather than bounding counterfactual effects2-layer MLP · Synthetic (20 nodes, 40 edges)unfairness: 0.170 vs 0.044 for CF-ICGHurt

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