Matching code and law: achieving algorithmic fairness with optimal transport
From MaRDI portal
Abstract: Increasingly, discrimination by algorithms is perceived as a societal and legal problem. As a response, a number of criteria for implementing algorithmic fairness in machine learning have been developed in the literature. This paper proposes the Continuous Fairness Algorithm (CFA) which enables a continuous interpolation between different fairness definitions. More specifically, we make three main contributions to the existing literature. First, our approach allows the decision maker to continuously vary between specific concepts of individual and group fairness. As a consequence, the algorithm enables the decision maker to adopt intermediate ``worldviews on the degree of discrimination encoded in algorithmic processes, adding nuance to the extreme cases of ``we're all equal (WAE) and ``what you see is what you get (WYSIWYG) proposed so far in the literature. Second, we use optimal transport theory, and specifically the concept of the barycenter, to maximize decision maker utility under the chosen fairness constraints. Third, the algorithm is able to handle cases of intersectionality, i.e., of multi-dimensional discrimination of certain groups on grounds of several criteria. We discuss three main examples (credit applications; college admissions; insurance contracts) and map out the legal and policy implications of our approach. The explicit formalization of the trade-off between individual and group fairness allows this post-processing approach to be tailored to different situational contexts in which one or the other fairness criterion may take precedence. Finally, we evaluate our model experimentally.
Recommendations
Cites work
- An algorithm for removing sensitive information: application to race-independent recidivism prediction
- Barycenters in the Wasserstein space
- Fairness through awareness
- scientific article; zbMATH DE number 5964375 (Why is no real title available?)
- scientific article; zbMATH DE number 4063438 (Why is no real title available?)
- scientific article; zbMATH DE number 6866333 (Why is no real title available?)
- Polar factorization and monotone rearrangement of vector‐valued functions
Cited in
(12)- How do fairness definitions fare? Testing public attitudes towards three algorithmic definitions of fairness in loan allocations
- Fairness in credit scoring: assessment, implementation and profit implications
- FairDEA -- removing disparate impact from efficiency scores
- Removing algorithmic discrimination (with minimal individual error)
- Fairness through awareness
- Individual fairness in hindsight
- Beyond submodularity: a unified framework of randomized set selection with group fairness constraints
- Countering racial discrimination in algorithmic lending: a case for model-agnostic interpretation methods
- Making individually fair predictions with causal pathways
- Studying bias in visual features through the lens of optimal transport
- Beyond incompatibility: trade-offs between mutually exclusive fairness criteria in machine learning and law
- Sparsification techniques for large-scale optimal transport problems
This page was built for publication: Matching code and law: achieving algorithmic fairness with optimal transport
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2218406)
