AI Paper Atlas

Research map / Learning theory and algorithms / Fairness

H-nobs: Achieving Certified Fairness and Robustness in Distributed Learning on Heterogeneous Datasets

Guanqiang Zhou, Ping Xu, Yue Wang, Zhi Tian

NeurIPS 2023 · Learning theory and algorithms › Fairness · approach: Fairness-constrained classification · 1 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
increase q-FFL q from 0 to 1 (ablation)H-nobs, beta=0 · Spambase, no attackvariance of local accuracy: 480 -> 269Improved
increase q-FFL q from 0 to 1 (ablation)H-nobs, beta=0 · Spambase, no attacktest accuracy: 92.5% -> 91.3%Hurt
increase q to 2 (ablation)H-nobs, beta=0 · Spambase, no attacktest accuracy: 91.3% -> 86.9%Hurt
increase screening beta from 0 to 30% at q=0 (ablation)H-nobs · Spambase, no attackvariance of local accuracy: 480 -> 392Improved
increase screening beta from 0 to 20% at q=1 (ablation)H-nobs · Spambase, no attackvariance of local accuracy: 269 -> 331Hurt
increase screening beta from 0 to 30% (ablation)H-nobs, q=0 · Spambase, no attacktest accuracy: 92.5% -> 92.2%No clear effect
increase screening beta from 0 to 20% at q=2 (ablation)H-nobs · Spambase, no attackvariance of local accuracy: 156 -> 243Hurt
add screening beta=10% at q=2 (ablation)H-nobs · Law School, no attacktest accuracy: 66.2% -> 73.3%Improved
increase screening beta from 0 to 10% at q=1 (ablation)H-nobs · Law School, no attackvariance of local accuracy: 353 -> 449Hurt
increase screening beta from 0 to 30% at q=0 (ablation)H-nobs · Law School, no attackvariance of local accuracy: 559 -> 507Improved
increase screening beta from 0 to 30% at q=2 (ablation)H-nobs · Credit Card Client, no attackvariance of local accuracy: 869 -> 966Hurt
increase screening beta from 0 to 30% at q=0 (ablation)H-nobs · Credit Card Client, no attackvariance of local accuracy: 1195 -> 1148Improved

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