AI Paper Atlas

Research map / Learning theory and algorithms / Fairness

FairALM: Augmented Lagrangian Method for Training Fair Models with Little Regret

Vishnu Suresh Lokhande, Aditya Kumar Akash, Sathya N. Ravi, Vikas Singh

ECCV 2020 · Learning theory and algorithms › Fairness · approach: Post-processing and transport for fairness · 22 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
replace Quadrianto et al. with FairALM constraintFairALM · CelebA (attractiveness, protected gender)DEO (%): 12.4 -> 10.4Improved
replace Fairness GAN with FairALMFairALM · CelebA (attractiveness, protected gender)DEO (%): 22.5 -> 10.4Improved
add FairALM fairness constraint to 3-layer ReLU net3-layer ReLU net · CelebA (40 labels)precision: +-5%No clear effect
use FairALM instead of naive l2 penaltyResNet-18 · CelebA (attractiveness)training stabilityImproved
add FairALM to unconstrained modelResNet-18 · ImSitu (Shaving vs Moisturize)DEO (%): 4.2 -> 0.0Improved
add FairALM to unconstrained modelResNet-18 · ImSitu (Cooking vs Driving)DEO (%): 7.1 -> 0.0Improved
add FairALM to unconstrained modelResNet-18 · ImSitu (Washing vs Saluting)DEO (%): 25.9 -> 0.0Improved
add FairALM to unconstrained modelResNet-18 · ImSitu (Assembling vs Hanging)DEO (%): 15.0 -> 0.0Improved
use FairALM instead of LagrangianResNet-18 · ImSitu (Shaving vs Moisturize)test error (ERR, %): 12.4 -> 20.0Hurt
use FairALM instead of Proxy-LagrangianResNet-18 · ImSitu (Assembling vs Hanging)DEO (%): 26.0 -> 0.0Improved
use FairALM for dataset pooling (site as protected variable)ResNet-18 · Chest X-ray TB (Shenzhen + Montgomery)test error varianceImproved
use FairALM instead of Agarwal et al.logistic regression · AdultDEO (%): 1.0 -> 0.7 ± 0.6Improved

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