AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Intra-Processing Methods for Debiasing Neural Networks

Yash Savani, Colin White, Naveen Sundar Govindarajulu

NeurIPS 2020 · Architectures and efficiency › Pruning and efficient tuning · approach: Parameter-efficient transfer analysis · 9 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 intra-processing instead of post-processingFine-tuned neural networks · Four evaluated datasetsobjective score under a bias constraintImproved
Use adversarial fine-tuning rather than random perturbation or layerwise optimizationCelebA ResNet model · CelebAbalanced accuracy under the fairness constraint: 0.914; 0.917; 0.905Improved
Train separate models with different random seedsNeural network · ACI (gender), BM (age), COMPAS (race)standard deviation of bias versus accuracy: 0.012; 0.017; 0.011; 0.002; 0.027; 0.051; 0.015; 0.002; 0.017; 0.027; 0.016; 0.006Mixed
Use a neural network instead of logistic regression or random forestTabular classification · ACIaccuracy: 0.852 $\pm$ 0.000; 0.855 $\pm$ 0.002; 0.844 $\pm$ 0.002Improved
Use a neural network instead of logistic regression or random forestTabular classification · BMaccuracy: 0.901 $\pm$ 0.000; 0.901 $\pm$ 0.002; 0.899 $\pm$ 0.001No clear effect
Use a neural network instead of logistic regression or random forestTabular classification · COMPASaccuracy: 0.677 $\pm$ 0.000; 0.641 $\pm$ 0.061; 0.652 $\pm$ 0.006Hurt

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