DeepAI AI Chat
Log In Sign Up

The Fairness-Accuracy Pareto Front

by   Susan Wei, et al.

Mitigating bias in machine learning is a challenging task, due in large part to the presence of competing objectives. Namely, a fair algorithm often comes at the cost of lower predictive accuracy, and vice versa, a highly predictive algorithm may be one that incurs high bias. This work presents a methodology for estimating the fairness-accuracy Pareto front of a fully-connected feedforward neural network, for any accuracy measure and any fairness measure. Our experiments firstly reveal that for training data already exhibiting disparities, a newly introduced causal notion of fairness may be capable of traversing a greater part of the fairness-accuracy space, relative to more standard measures such as demographic parity and conditional parity. The experiments also reveal that tools from multi-objective optimisation are crucial in efficiently estimating the Pareto front (i.e., by finding more non-dominated points), relative to other sensible but ad-hoc approaches. Finally, the work serves to highlight possible synergy between deep learning and multi-objective optimisation. Given that deep learning is increasingly deployed in real-world decision making, the Pareto front can provide a formal way to reason about inherent conflicts.


page 1

page 2

page 3

page 4


Accuracy and Fairness Trade-offs in Machine Learning: A Stochastic Multi-Objective Approach

In the application of machine learning to real-life decision-making syst...

Using Pareto Simulated Annealing to Address Algorithmic Bias in Machine Learning

Algorithmic Bias can be due to bias in the training data or issues with ...

Pareto Efficient Fairness in Supervised Learning: From Extraction to Tracing

As algorithmic decision-making systems are becoming more pervasive, it i...

Generalization In Multi-Objective Machine Learning

Modern machine learning tasks often require considering not just one but...

Mitigating Unfairness via Evolutionary Multi-objective Ensemble Learning

In the literature of mitigating unfairness in machine learning, many fai...

Achieving Fairness through Adversarial Learning: an Application to Recidivism Prediction

Recidivism prediction scores are used across the USA to determine senten...