DeepAI AI Chat
Log In Sign Up

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

02/17/2023
by   Mohammad Yaghini, et al.
0

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.

READ FULL TEXT

page 12

page 13

page 23

08/13/2021

The Sharpe predictor for fairness in machine learning

In machine learning (ML) applications, unfair predictions may discrimina...
05/22/2023

Causality-Aided Trade-off Analysis for Machine Learning Fairness

There has been an increasing interest in enhancing the fairness of machi...
02/15/2023

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

This paper investigates to what degree and magnitude tradeoffs exist bet...
03/31/2021

Achieving Transparency Report Privacy in Linear Time

An accountable algorithmic transparency report (ATR) should ideally inve...
04/26/2022

Scheduling Virtual Conferences Fairly: Achieving Equitable Participant and Speaker Satisfaction

Recently, almost all conferences have moved to virtual mode due to the p...
03/03/2023

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

Machine Learning (ML) architectures have been applied to several applica...
03/15/2020

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

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