AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Does enforcing fairness mitigate biases caused by subpopulation shift?

Subha Maity, Debarghya Mukherjee, Mikhail Yurochkin, Yuekai Sun

NeurIPS 2021 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Mixture and distillation for domain shift · 6 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
Enforce tight Equalized Odds during training instead of using a loose fairness constraintReductions with logistic regression · COMPAS, target distribution P*accuracy: 0.634±0.011 -> 0.652±0.013; 1.8% higherImproved
Enforce tight Equalized Odds during training instead of using a loose fairness constraintReductions with logistic regression · COMPAS, training distribution P̃accuracy: 0.668±0.010 -> 0.660±0.009; 0.8%Hurt
Enforce tight Equalized Odds during training instead of using a loose fairness constraintReductions with logistic regression · Adult, target distribution P*accuracy: 0.848±0.005 -> 0.852±0.004Improved
Enforce tight Equalized Odds during training instead of using a loose fairness constraintReductions with logistic regression · Adult, training distribution P̃accuracy: 0.847±0.003 -> 0.843±0.003Hurt
Enforce Equalized Odds during training on biased simulated dataReductions with logistic regression · Simulated data, target distribution P*accuracy: +3%Improved
Enforce Equalized Odds during training on biased simulated dataReductions with logistic regression · Simulated data, training distribution P̃accuracy: 1% less accurateHurt
Enforce risk parity rather than minimize risk without a fairness constraintRisk minimization under subpopulation shift · Target domain; outcome depends on target group proportionsoverall riskMixed
Enforce fairness when the target-domain Bayes decision rule is fairFair risk minimization under subpopulation shift · Target domainoverall riskMixed

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