AI Paper Atlas

Research map / Learning theory and algorithms / Fairness

Exploiting MMD and Sinkhorn Divergences for Fair and Transferable Representation Learning

Luca Oneto, Michele Donini, Giulia Luise, Carlo Ciliberto, Andreas Maurer, Massimiliano Pontil

NeurIPS 2020 · Learning theory and algorithms › Fairness · approach: Fairness-constrained classification

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
add Sinkhorn-divergence fairness constraint on shared representationshared-representation FFNN · School new tasks (linear)DDP: .088 -> .017Improved
add Sinkhorn constraint, unconstrained model as referenceshared-representation FFNN · School new tasks (linear)ERR: 13.8 -> 14.8Hurt
replace M [13] with Sinkhorn-constrained representationshared-representation FFNN · UNIV new tasks (linear)DDP: .033 -> .009Improved
replace M [13] with Sinkhorn-constrained representationshared-representation FFNN · UNIV new tasks (linear)ERR: 27.3 -> 16.0Improved
use Gaussian-kernel MMD instead of mean matching (ablation)shared-representation FFNN · School new tasks (linear)DDP: .022 -> .020Improved
use Sinkhorn instead of mean matching (ablation)shared-representation FFNN · UNIV new tasks (linear)DDP: .015 -> .009Improved
use Sinkhorn instead of mean matching (ablation)shared-representation FFNN · Movielens new tasks (linear)DDP: .016 -> .011Improved
replace M [12] output-level constraint with Sinkhorn representation constraintshared-representation FFNN · Movielens new tasks (linear)DDP: .025 -> .011Improved
replace linear with sigmoid activation in representation (ablation)shared-representation FFNN · School new tasksERR: 14.8 -> 10.2Improved
add Sinkhorn fairness constraint with sigmoid representationshared-representation FFNN · UNIV new tasksDDP: .175 -> .115Mixed
replace Sinkhorn with M [13] on non-linear modelshared-representation FFNN · UNIV new tasks (sigmoid)DDP: .101 -> .115Hurt
fairness constraint [12] on output with sensitive feature in modelM [12] · UNIV new tasks (sigmoid)DDP: .212 -> .241Hurt

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