AI Paper Atlas

Research map / Learning theory and algorithms / Fairness

DeepGemini: Verifying Dependency Fairness for Deep Neural Network

Xuan Xie, Fuyuan Zhang, Xinwen Hu, Lei Ma

AAAI 2023 · Learning theory and algorithms › Fairness · approach: Fairness auditing and regularization · 7 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
Use DeepGemini's SM-random fairness analysis instead of Libra-SymbolicCOMPAS DNNs with five hidden layers · COMPASfairness score (%): 51.48% vs 26.79%Improved
Apply iterative region refinement in CEGFADeepGemini · German credit and COMPASfairness scoreImproved
Train on the fair rather than biased dataset versionDNNs analyzed by DeepGemini · German credit and COMPASfairness scoreImproved
Use random, saliency-map, important-neuron, or ε-greedy region refinement (ablation)CEGFA · German credit and COMPASfairness scoreMixed
Increase DNN size from four hidden layers with 20 neurons per layer to four hidden layers with 30 neurons per layerDeepGemini · COMPAS; query QC1verification time (seconds): 37.0 -> 225.96Hurt

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