FairMask: Better Fairness via Model-based Rebalancing of Protected Attributes

Abstract

Context: Machine learning software can generate models that inappropriately discriminate against specific protected social groups (e.g., groups based on gender, ethnicity, etc). Motivated by those results, software engineering researchers have proposed many methods for mitigating those discriminatory effects. While those methods are effective in mitigating bias, few of them can provide explanations on what is the root cause of bias. Objective: We aim at better detection and mitigation of algorithmic discrimination in machine learning software problems. Method: Here we propose xFAIR, a model-based extrapolation method, that is capable of both mitigating bias and explaining the cause. In our xFAIR approach, protected attributes are represented by models learned from the other independent variables (and these models offer extrapolations over the space between existing examples). We then use the extrapolation models to relabel protected attributes later seen in testing data or deployment time. Our approach aims to offset the biased predictions of the classification model via rebalancing the distribution of protected attributes. Results: The experiments of this paper show that, without compromising (original) model performance, xFAIR can achieve significantly better group and individual fairness (as measured in different metrics) than benchmark methods. Moreover, when compared to another instance-based rebalancing method, our model-based approach shows faster runtime and thus better scalability. Conclusion: Algorithmic decision bias can be removed via extrapolation that smooths away outlier points. As evidence for this, our proposed xFAIR is not only performance-wise better (measured by fairness and performance metrics) than two state-of-the-art fairness algorithms.

14 pages, 6 figures, 7 tables, accepted by TSE

References in corpus (9)

• SMOTE: Synthetic Minority Over-sampling Technique
• Fairness Testing: Testing Software for Discrimination
• On Fairness and Calibration
• AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias
• Flexibly Fair Representation Learning by Disentanglement
• Do the Machine Learning Models on a Crowd Sourced Platform Exhibit Bias? An Empirical Study on Model Fairness
• Hyperparameter Optimization for Effort Estimation
• Software Engineering for Fairness: A Case Study with Hyperparameter Optimization
• README: REpresentation learning by fairness-Aware Disentangling MEthod