Using Pareto Simulated Annealing to Address Algorithmic Bias in Machine Learning
This addresses fairness issues in ML models for applications where bias can lead to harmful outcomes, but it is incremental as it builds on existing multi-objective optimization methods.
The paper tackled algorithmic bias in machine learning by proposing a multi-objective optimization strategy using Pareto Simulated Annealing to optimize for both balanced accuracy and underestimation, demonstrating its effectiveness on one synthetic and two real-world datasets.
Algorithmic Bias can be due to bias in the training data or issues with the algorithm itself. These algorithmic issues typically relate to problems with model capacity and regularisation. This underestimation bias may arise because the model has been optimised for good generalisation accuracy without any explicit consideration of bias or fairness. In a sense, we should not be surprised that a model might be biased when it hasn't been "asked" not to be. In this paper, we consider including bias (underestimation) as an additional criterion in model training. We present a multi-objective optimisation strategy using Pareto Simulated Annealing that optimise for both balanced accuracy and underestimation. We demonstrate the effectiveness of this strategy on one synthetic and two real-world datasets.