Post-Hoc Methods for Debiasing Neural Networks

06/15/2020
by   Yash Savani, et al.
18

As deep learning models become tasked with more and more decisions that impact human lives, such as hiring, criminal recidivism, and loan repayment, bias is becoming a growing concern. This has led to dozens of definitions of fairness and numerous algorithmic techniques to improve the fairness of neural networks. Most debiasing algorithms require retraining a neural network from scratch, however, this is not feasible in many applications, especially when the model takes days to train or when the full training dataset is no longer available. In this work, we present a study on post-hoc methods for debiasing neural networks. First we study the nature of the problem, showing that the difficulty of post-hoc debiasing is highly dependent on the initial conditions of the original model. Then we define three new fine-tuning techniques: random perturbation, layer-wise optimization, and adversarial fine-tuning. All three techniques work for any group fairness constraint. We give a comparison with six algorithms - three popular post-processing debiasing algorithms and our three proposed methods - across three datasets and three popular bias measures. We show that no post-hoc debiasing technique dominates all others, and we identify settings in which each algorithm performs the best. Our code is available at https://github.com/realityengines/post_hoc_debiasing.

READ FULL TEXT
research
04/08/2023

Last-Layer Fairness Fine-tuning is Simple and Effective for Neural Networks

As machine learning has been deployed ubiquitously across applications i...
research
06/22/2023

Data-Free Backbone Fine-Tuning for Pruned Neural Networks

Model compression techniques reduce the computational load and memory co...
research
06/01/2022

FETA: Fairness Enforced Verifying, Training, and Predicting Algorithms for Neural Networks

Algorithmic decision making driven by neural networks has become very pr...
research
03/02/2021

Fast Adaptation with Linearized Neural Networks

The inductive biases of trained neural networks are difficult to underst...
research
07/26/2022

Debiasing Deep Chest X-Ray Classifiers using Intra- and Post-processing Methods

Deep neural networks for image-based screening and computer-aided diagno...
research
02/14/2023

A modern look at the relationship between sharpness and generalization

Sharpness of minima is a promising quantity that can correlate with gene...
research
01/14/2022

When less is more: Simplifying inputs aids neural network understanding

How do neural network image classifiers respond to simpler and simpler i...

Please sign up or login with your details

Forgot password? Click here to reset