DeepAI AI Chat
Log In Sign Up

Learning with Impartiality to Walk on the Pareto Frontier of Fairness, Privacy, and Utility

by   Mohammad Yaghini, et al.

Deploying machine learning (ML) models often requires both fairness and privacy guarantees. Both of these objectives present unique trade-offs with the utility (e.g., accuracy) of the model. However, the mutual interactions between fairness, privacy, and utility are less well-understood. As a result, often only one objective is optimized, while the others are tuned as hyper-parameters. Because they implicitly prioritize certain objectives, such designs bias the model in pernicious, undetectable ways. To address this, we adopt impartiality as a principle: design of ML pipelines should not favor one objective over another. We propose impartially-specified models, which provide us with accurate Pareto frontiers that show the inherent trade-offs between the objectives. Extending two canonical ML frameworks for privacy-preserving learning, we provide two methods (FairDP-SGD and FairPATE) to train impartially-specified models and recover the Pareto frontier. Through theoretical privacy analysis and a comprehensive empirical study, we provide an answer to the question of where fairness mitigation should be integrated within a privacy-aware ML pipeline.


page 12

page 13

page 23


The Sharpe predictor for fairness in machine learning

In machine learning (ML) applications, unfair predictions may discrimina...

Causality-Aided Trade-off Analysis for Machine Learning Fairness

There has been an increasing interest in enhancing the fairness of machi...

Evaluating Trade-offs in Computer Vision Between Attribute Privacy, Fairness and Utility

This paper investigates to what degree and magnitude tradeoffs exist bet...

Achieving Transparency Report Privacy in Linear Time

An accountable algorithmic transparency report (ATR) should ideally inve...

Scheduling Virtual Conferences Fairly: Achieving Equitable Participant and Speaker Satisfaction

Recently, almost all conferences have moved to virtual mode due to the p...

Exploring Machine Learning Privacy/Utility trade-off from a hyperparameters Lens

Machine Learning (ML) architectures have been applied to several applica...

Balancing Competing Objectives with Noisy Data: Score-Based Classifiers for Welfare-Aware Machine Learning

While real-world decisions involve many competing objectives, algorithmi...