AI Paper Atlas

Research map / Learning theory and algorithms / Fairness

Task-Tailored Pre-Processing: Fair Downstream Supervised Learning

Jinwon Sohn, Qifan Song, Guang Lin

TPAMI 2026 · Learning theory and algorithms › Fairness · approach: Fairness-constrained classification · 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 delta_Y=0.1 (modify labels) instead of delta_Y=0 (ablation)Task-tailored pre-processing · ACSPublicCoverageAUC-MP (Budget 1): .715 -> .804Improved
use delta_Y=0.1 instead of 0 (ablation)Task-tailored pre-processing · ACSPublicCoverageAUC-RF (Budget 1): .731 -> .816Improved
use delta_Y=0.1 instead of 0 (ablation)Task-tailored pre-processing · ACSPublicCoverageconsistency of utility sigma_AUC-SP (Budget 1): .023 -> .015Improved
use delta_Y=0.1 instead of 0 (ablation)Task-tailored pre-processing · ACSPublicCoverageconsistency of fairness sigma_SP (Budget 2): .292 -> .207Improved
use delta_Y=0.1 instead of 0 (ablation)Task-tailored pre-processing · ACSPublicCoveragesigma_KS-SP (Budget 2): .123 -> .087Improved
use Ours instead of FAAP for downstream fairnessFAAP · CelebA Blond Hair (delta_X=.010)downstream Delta EO: approx 0 -> .229Improved
use Ours instead of FAAP for downstream fairnessFAAP · CelebA Blond Hair (delta_X=.015)downstream Delta EO: -.067 -> .231Improved
raise fairness budget delta_X from 0 to .010 (ablation)Task-tailored pre-processing · CelebA SmilingP(h=1|A=1): .397 -> .427Improved
raise fairness budget delta_X from 0 to .010 (female group) (ablation)Task-tailored pre-processing · CelebA SmilingP(h=1|A=0): .531 -> .511Improved
raise delta_X from 0 to .015 (ablation)Task-tailored pre-processing · CelebA Blond HairP_{1,1}(Y=1): .663 -> .784Improved
raise delta_X from 0 to .015 (ablation)Task-tailored pre-processing · CelebA Blond HairAUC (upstream): .975 -> .963Hurt
use task-tailored pre-processing instead of data-fairness approachesTask-tailored pre-processing · tabular benchmarksAUC vs SP trade-offImproved

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