Do the Machine Learning Models on a Crowd Sourced Platform Exhibit Bias? An Empirical Study on Model Fairness

Abstract

Machine learning models are increasingly being used in important decision-making software such as approving bank loans, recommending criminal sentencing, hiring employees, and so on. It is important to ensure the fairness of these models so that no discrimination is made based on protected attribute (e.g., race, sex, age) while decision making. Algorithms have been developed to measure unfairness and mitigate them to a certain extent. In this paper, we have focused on the empirical evaluation of fairness and mitigations on real-world machine learning models. We have created a benchmark of 40 top-rated models from Kaggle used for 5 different tasks, and then using a comprehensive set of fairness metrics, evaluated their fairness. Then, we have applied 7 mitigation techniques on these models and analyzed the fairness, mitigation results, and impacts on performance. We have found that some model optimization techniques result in inducing unfairness in the models. On the other hand, although there are some fairness control mechanisms in machine learning libraries, they are not documented. The mitigation algorithm also exhibit common patterns such as mitigation in the post-processing is often costly (in terms of performance) and mitigation in the pre-processing stage is preferred in most cases. We have also presented different trade-off choices of fairness mitigation decisions. Our study suggests future research directions to reduce the gap between theoretical fairness aware algorithms and the software engineering methods to leverage them in practice.

To be appeared in ESEC/FSE 2020

References in corpus (15)

• Equality of Opportunity in Supervised Learning
• DeepXplore: Automated Whitebox Testing of Deep Learning Systems
• Improving fairness in machine learning systems: What do industry practitioners need?
• Fairness Testing: Testing Software for Discrimination
• Fairness in Machine Learning: Lessons from Political Philosophy
• Fairness Constraints: Mechanisms for Fair Classification
• On Fairness and Calibration
• AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias
• Automated Directed Fairness Testing
• A Unified Approach to Quantifying Algorithmic Unfairness: Measuring Individual & Group Unfairness via Inequality Indices
• Multi-task Neural Networks for QSAR Predictions
• Fairness Under Unawareness: Assessing Disparity When Protected Class Is Unobserved
• Iterative Orthogonal Feature Projection for Diagnosing Bias in Black-Box Models
• Symbolic Execution for Deep Neural Networks
• FAT Forensics: A Python Toolbox for Algorithmic Fairness, Accountability and Transparency

Cited by in corpus (16)

• Machine Learning at the Network Edge: A Survey
• Bias in Machine Learning Software: Why? How? What to do?
• Fair Preprocessing: Towards Understanding Compositional Fairness of Data Transformers in Machine Learning Pipeline
• The Art and Practice of Data Science Pipelines: A Comprehensive Study of Data Science Pipelines In Theory, In-The-Small, and In-The-Large
• Towards Understanding Fairness and its Composition in Ensemble Machine Learning
• To Be Forgotten or To Be Fair: Unveiling Fairness Implications of Machine Unlearning Methods
• Manas: Mining Software Repositories to Assist AutoML
• FairBalance: How to Achieve Equalized Odds With Data Pre-processing
• Fix Fairness, Don't Ruin Accuracy: Performance Aware Fairness Repair using AutoML
• Fairness Hacking: The Malicious Practice of Shrouding Unfairness in Algorithms
• Fair-SSL: Building fair ML Software with less data
• FairMask: Better Fairness via Model-based Rebalancing of Protected Attributes
• FairGridSearch: A Framework to Compare Fairness-Enhancing Models
• A Survey of Algorithm Debt in Machine and Deep Learning Systems: Definition, Smells, and Future Work
• DeepLocalize: Fault Localization for Deep Neural Networks
• Uncovering Discrimination Clusters: Quantifying and Explaining Systematic Fairness Violations