Enhancing Fairness and Performance in Machine Learning Models: A Multi-Task Learning Approach with Monte-Carlo Dropout and Pareto Optimality
This addresses fairness issues in ML models for applications where bias from data and algorithms is critical, though it appears incremental as it builds on existing methods like MTL and MC Dropout.
The study tackled bias in machine learning by using a multi-task learning framework with Monte Carlo Dropout and Pareto optimality to balance fairness and performance, demonstrating effectiveness across multiple datasets with enhanced interpretability.
Bias originates from both data and algorithmic design, often exacerbated by traditional fairness methods that fail to address the subtle impacts of protected attributes. This study introduces an approach to mitigate bias in machine learning by leveraging model uncertainty. Our approach utilizes a multi-task learning (MTL) framework combined with Monte Carlo (MC) Dropout to assess and mitigate uncertainty in predictions related to protected labels. By incorporating MC Dropout, our framework quantifies prediction uncertainty, which is crucial in areas with vague decision boundaries, thereby enhancing model fairness. Our methodology integrates multi-objective learning through pareto-optimality to balance fairness and performance across various applications. We demonstrate the effectiveness and transferability of our approach across multiple datasets and enhance model explainability through saliency maps to interpret how input features influence predictions, thereby enhancing the interpretability of machine learning models in practical applications.