Bias in Machine Learning Software: Why? How? What to do?

Abstract

Increasingly, software is making autonomous decisions in case of criminal sentencing, approving credit cards, hiring employees, and so on. Some of these decisions show bias and adversely affect certain social groups (e.g. those defined by sex, race, age, marital status). Many prior works on bias mitigation take the following form: change the data or learners in multiple ways, then see if any of that improves fairness. Perhaps a better approach is to postulate root causes of bias and then applying some resolution strategy. This paper postulates that the root causes of bias are the prior decisions that affect- (a) what data was selected and (b) the labels assigned to those examples. Our Fair-SMOTE algorithm removes biased labels; and rebalances internal distributions such that based on sensitive attribute, examples are equal in both positive and negative classes. On testing, it was seen that this method was just as effective at reducing bias as prior approaches. Further, models generated via Fair-SMOTE achieve higher performance (measured in terms of recall and F1) than other state-of-the-art fairness improvement algorithms. To the best of our knowledge, measured in terms of number of analyzed learners and datasets, this study is one of the largest studies on bias mitigation yet presented in the literature.

References in corpus (6)

• SMOTE: Synthetic Minority Over-sampling Technique
• Fairness Testing: Testing Software for Discrimination
• Automated Directed Fairness Testing
• Fairway: A Way to Build Fair ML Software
• Do the Machine Learning Models on a Crowd Sourced Platform Exhibit Bias? An Empirical Study on Model Fairness
• Making Fair ML Software using Trustworthy Explanation

Cited by in corpus (10)

• On Leakage in Machine Learning Pipelines
• Latent Imitator: Generating Natural Individual Discriminatory Instances for Black-Box Fairness Testing
• Towards Understanding Fairness and its Composition in Ensemble Machine Learning
• Diversity's Double-Edged Sword: Analyzing Race's Effect on Remote Pair Programming Interactions
• FairBalance: How to Achieve Equalized Odds With Data Pre-processing
• Fix Fairness, Don't Ruin Accuracy: Performance Aware Fairness Repair using AutoML
• Fair-SSL: Building fair ML Software with less data
• FairIF: Boosting Fairness in Deep Learning via Influence Functions with Validation Set Sensitive Attributes
• Model Review: A PROMISEing Opportunity
• Uncovering Discrimination Clusters: Quantifying and Explaining Systematic Fairness Violations