Balancing Fairness and Accuracy in Data-Restricted Binary Classification
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914711038066688 |
|---|---|
| author | Lazri, Zachary McBride Dervovic, Danial Polychroniadou, Antigoni Brugere, Ivan Dachman-Soled, Dana Wu, Min |
| author_facet | Lazri, Zachary McBride Dervovic, Danial Polychroniadou, Antigoni Brugere, Ivan Dachman-Soled, Dana Wu, Min |
| contents | Applications that deal with sensitive information may have restrictions placed on the data available to a machine learning (ML) classifier. For example, in some applications, a classifier may not have direct access to sensitive attributes, affecting its ability to produce accurate and fair decisions. This paper proposes a framework that models the trade-off between accuracy and fairness under four practical scenarios that dictate the type of data available for analysis. Prior works examine this trade-off by analyzing the outputs of a scoring function that has been trained to implicitly learn the underlying distribution of the feature vector, class label, and sensitive attribute of a dataset. In contrast, our framework directly analyzes the behavior of the optimal Bayesian classifier on this underlying distribution by constructing a discrete approximation it from the dataset itself. This approach enables us to formulate multiple convex optimization problems, which allow us to answer the question: How is the accuracy of a Bayesian classifier affected in different data restricting scenarios when constrained to be fair? Analysis is performed on a set of fairness definitions that include group and individual fairness. Experiments on three datasets demonstrate the utility of the proposed framework as a tool for quantifying the trade-offs among different fairness notions and their distributional dependencies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_07724 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Balancing Fairness and Accuracy in Data-Restricted Binary Classification Lazri, Zachary McBride Dervovic, Danial Polychroniadou, Antigoni Brugere, Ivan Dachman-Soled, Dana Wu, Min Machine Learning Artificial Intelligence Computers and Society Applications that deal with sensitive information may have restrictions placed on the data available to a machine learning (ML) classifier. For example, in some applications, a classifier may not have direct access to sensitive attributes, affecting its ability to produce accurate and fair decisions. This paper proposes a framework that models the trade-off between accuracy and fairness under four practical scenarios that dictate the type of data available for analysis. Prior works examine this trade-off by analyzing the outputs of a scoring function that has been trained to implicitly learn the underlying distribution of the feature vector, class label, and sensitive attribute of a dataset. In contrast, our framework directly analyzes the behavior of the optimal Bayesian classifier on this underlying distribution by constructing a discrete approximation it from the dataset itself. This approach enables us to formulate multiple convex optimization problems, which allow us to answer the question: How is the accuracy of a Bayesian classifier affected in different data restricting scenarios when constrained to be fair? Analysis is performed on a set of fairness definitions that include group and individual fairness. Experiments on three datasets demonstrate the utility of the proposed framework as a tool for quantifying the trade-offs among different fairness notions and their distributional dependencies. |
| title | Balancing Fairness and Accuracy in Data-Restricted Binary Classification |
| topic | Machine Learning Artificial Intelligence Computers and Society |
| url | https://arxiv.org/abs/2403.07724 |