AI Paper Atlas

Research map / Learning theory and algorithms / Fairness

PC-Fairness: A Unified Framework for Measuring Causality-based Fairness

Yongkai Wu, Lu Zhang, Xintao Wu, Hanghang Tong

NeurIPS 2019 · Learning theory and algorithms › Fairness · approach: Post-processing and transport for fairness · 44 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 PC-fairness LP bounds instead of previous Markovian bounding method for path-specific effectBounds on PE · Synthetic D2bound width: [-0.2605, 0.2656] -> [0.1772, 0.1836]Improved
use PC-fairness LP bounds instead of previous bounding method for counterfactual effectBounds on CE group 2 · Synthetic D2bound width: [-0.4383, -0.0212] -> [-0.0783, -0.0212]Improved
use PC-fairness LP bounds instead of previous method for CEBounds on CE group 1 · Synthetic D2bound width: [0.0878, 0.5049] -> [0.0878, 0.5049]No clear effect
use PC-fairness LP bounds instead of previous method for CEBounds on CE group 4 · Adultbound width: [0.1676, 0.5289] -> [0.4419, 0.5289]Improved
use PC-fairness LP bounds instead of previous method for CEBounds on CE group 1 · Adultbound width: [-0.1314, 0.1091] -> [-0.1314, 0.1091]No clear effect
LP bounds validity check against ground truthPC fairness bounds · Synthetic D1 with hidden confoundertruth within bounds: e.g. truth 0.1507 within [-0.4548, 0.5452]Improved

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