AI Paper Atlas

Research map / Learning theory and algorithms / Fairness

Are My Deep Learning Systems Fair? An Empirical Study of Fixed-Seed Training

Shangshu Qian, Hung Viet Pham, Thibaud Lutellier, Zeou Hu, Jungwon Kim, Lin Tan, Yaoliang Yu, Jiahao Chen, Sameena Shah

NeurIPS 2021 · Learning theory and algorithms › Fairness · approach: Fairness auditing and regularization · 20 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
fix random seed across identical training runsDL fairness training · 27 techniques, 16 fixed-seed runsbias metrics (DP, DI, etc.): up to 12.6% DP max differenceNo clear effect
apply debiasing algorithm GR vs baseline, averaged over 16 runsS-Base · BA metricbias amplification (%): 7.4 -> 8.7Hurt
apply 22 debiasing techniquesbaseline DL models · 7 bias metrics, 154 experimentsbias values: 103 of 154 reduce bias; 15 of 22 techniques increase at least one metricMixed
apply debiasing that reduces biasbaseline DL models · 103 bias-reducing experimentsaccuracy and variance costs: 70 of 103 with costHurt
apply RBA debiasing (S-DD4)S-Base · 7 bias metricsbias and varianceImproved

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