AI Paper Atlas

Research map / Learning theory and algorithms / Fairness

Chasing Fairness Under Distribution Shift: A Model Weight Perturbation Approach

Zhimeng Jiang, Xiaotian Han, Hongye Jin, Guanchu Wang, Rui Chen, Na Zou, Xia Hu

NeurIPS 2023 · Learning theory and algorithms › Fairness · approach: Fairness-constrained classification · 4 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 RFR instead of the second-best baseline under mild synthetic shiftRFR · Adult (1.0, 2.0) synthetic shiftdemographic parity gap: 47.0%Improved
Use RFR instead of the second-best baseline under mild synthetic shiftRFR · Adult (1.0, 2.0) synthetic shiftequal opportunity gap: 84.8%Improved
Increase synthetic shift intensity from (1.0, 2.0) to (3.0, 6.0)RFR · Adult synthetic shiftdemographic parity gap: 0.44 -> 1.75Hurt
Use RFR instead of the second-best baseline under temporal shiftRFR · ACS-I 2016->2018demographic parity gap: 34.9%Improved
Use RFR instead of the second-best baseline under temporal shiftRFR · ACS-I 2016->2018equal opportunity gap: 34.4%Improved
Use RFR instead of ADV under spatial shift MI to CARFR · ACS-Idemographic parity gap: 1.04 -> 1.35Hurt
Increase lambda from 0.0 toward 10.0 (ablation)RFR · ACS spatial and temporal shiftaccuracy and demographic parityMixed
Vary perturbation radius rho (ablation)RFR · ACS-I and ACS-Eaccuracy and demographic parityMixed
Remove L_DP term from the RFR objective (ablation)RFR · ACS-I and ACS-Edemographic parity gapImproved
Remove distribution shift (random split) vs RFR under 2016->2018 shiftRFR · ACS-Idemographic parity gap: 1.36 -> 1.88Hurt
Use REG instead of RFR without distribution shiftRFR · ACS-Edemographic parity gap: 1.09 -> 1.05Improved

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