Robust Optimization for Fairness with Noisy Protected Groups

By Serena Wang, Wenshuo Guo, Harikrishna Narasimhan, Andrew Cotter, Maya R. Gupta, Michael I. Jordan. 2020

129 citations recorded by the source corpus.

Many existing fairness criteria for machine learning involve equalizing some metric across \textit{protected groups} such as race or gender. However, practitioners trying to audit or enforce such group-based criteria can easily face the problem of noisy or biased protected group information. First, we study the consequences of na{i}vely relying on noisy protected group labels: we provide an upper bound on the fairness violations on the true groups $G$ when the fairness criteria are satisfied on noisy groups $\hat{G}$. Second, we introduce two new approaches using robust optimization that, unlike the na{i}ve approach of only relying on $\hat{G}$, are guaranteed to satisfy fairness criteria on the true protected groups $G$ while minimizing a training objective. We provide theoretical guarantees that one such approach converges to an optimal feasible solution. Using two case studies, we show empirically that the robust approaches achieve better true group fairness guarantees than the na{i}ve approach.

Subfields: Artificial Intelligence, Management Science and Operations Research, Safety Research

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Management Science and Operations Research

In Safety Research

Citations in the corpus

A Survey on the Fairness of Recommender Systems (2022, background): “There has been some related work on classification tasks [17, 18, 48, 92, 100], while in recommender systems, it is still a problem to be explored.”
No Subclass Left Behind: Fine-Grained Robustness in Coarse-Grained Classification Problems (2020, background): “[56] Serena Wang, Wenshuo Guo, Harikrishna Narasimhan, Andrew Cotter, Maya Gupta, and Michael Jordan.”
Uncertainty as a Form of Transparency: Measuring, Communicating, and Using Uncertainty (2020, methodology): “When little or no information about the sensitive attribute is available, distributionally robust optimization can be used to enforce fairness constraints [67, 181].”
Data collection and quality challenges in deep learning: a data-centric AI perspective (2021, background): “An analysis of fair training results on noisy sensitive group information [168] shows that the true fairness violation on a clean sensitive group can be bounded by a distance between this group and its noisy version.”
It's COMPASlicated: The Messy Relationship between RAI Datasets and Algorithmic Fairness Benchmarks (2021, unknown): “[42] studies robust evaluation and classification.”