AI Paper Atlas

Research map / Learning theory and algorithms / Fairness

FR-Train: A Mutual Information-Based Approach to Fair and Robust Training

Yuji Roh, Kangwook Lee, Steven Whang, Changho Suh

ICML 2020 · Learning theory and algorithms › Fairness · approach: Fairness-constrained classification · 13 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
jointly train with fairness and robustness discriminators and example re-weightingFR-Train · Synthetic, COMPAS, and AdultCensus poisoned test dataaccuracy: Synthetic .814; COMPAS .670; AdultCensus .809Improved
jointly optimize fairness and robustness rather than fairness alone (ablation)FR-Train · COMPAS, poisonedaccuracy: .580 -> .670Improved
add robust training (ablation)FR-Train · COMPAS, poisoneddisparate impact: .802 -> .846Improved
add fair training (ablation)FR-Train · COMPAS, poisoneddisparate impact: .420 -> .846Improved
add example re-weighting (ablation)FR-Train · COMPAS, poisonedaccuracy: .624 -> .670Improved
use a 5% clean validation setFR-Train · Synthetic poisoned dataaccuracy-fairness tradeoffNo clear effect
use a 0.1% validation setFR-Train · Synthetic poisoned dataaccuracy-fairness tradeoffHurt
decrease λ₂ to 0.1 with a very small validation setFR-Train · Synthetic poisoned dataaccuracy-fairness tradeoffImproved
apply RML sanitization before fairness trainingFC · Synthetic, poisonedaccuracy: .760 -> .529Hurt
increase crowdsourced answers averaged per example from N = 1 to N = 11Crowdsourced validation labels · COMPASlabel accuracy: 0.609 -> 0.667Improved
use FR-Train with equalized-odds fairness instead of logistic regressionSynthetic data · Synthetic test dataequalized odds, Y = 0: 0.351 -> 0.888Improved

Later papers that compared with this method

2 later accepted papers report FRTrain as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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