An official website of the United States government
As algorithmic decision making is increasingly deployed in every walk of life, many researchers have raised concerns about fairness-related bias from such algorithms. But there is little research on harnessing psychometric methods to uncover potential discriminatory bias inside decision-making algorithms. The main goal of this article is to propose a new framework for algorithmic fairness based on differential item functioning (DIF), which has been commonly used to measure item fairness in psychometrics. Our fairness notion, which we call differential algorithmic functioning (DAF), is defined based on three pieces of information: a decision variable, a “fair” variable, and a protected variable such as race or gender. Under the DAF framework, an algorithm can exhibit uniform DAF, nonuniform DAF, or neither (i.e., non-DAF). For detecting DAF, we provide modifications of well-established DIF methods: Mantel–Haenszel test, logistic regression, and residual-based DIF. We demonstrate our framework through a real dataset concerning decision-making algorithms for grade retention in K–12 education in the United States.
more »
« less
This content will become publicly available on September 14, 2025
Evaluating Intersectional Fairness in Algorithmic Decision Making Using Intersectional Differential Algorithmic Functioning
Ensuring fairness is crucial in developing modern algorithms and tests. To address potential biases and discrimination in algorithmic decision making, researchers have drawn insights from the test fairness literature, notably the work on differential algorithmic functioning (DAF) by Suk and Han. Nevertheless, the exploration of intersectionality in fairness investigations, within both test fairness and algorithmic fairness fields, is still relatively new. In this paper, we propose an extension of the DAF framework to include the concept of intersectionality. Similar to DAF, the proposed notion for intersectionality, which we term “interactive DAF,” leverages ideas from test fairness and algorithmic fairness. We also provide methods based on the generalized Mantel–Haenszel test, generalized logistic regression, and regularized group regression to detect DAF, interactive DAF, or other subtypes of DAF. Specifically, we employ regularized group regression with three different penalties and examine their performance via a simulation study. Finally, we demonstrate our intersectional DAF framework in real-world applications on grade retention and conditional cash transfer programs in education.
more »
« less
- Award ID(s):
- 2225321
- PAR ID:
- 10541811
- Publisher / Repository:
- DOI PREFIX: 10.3102
- Date Published:
- Journal Name:
- Journal of Educational and Behavioral Statistics
- ISSN:
- 1076-9986
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Algorithmic fairness is becoming increasingly important in data mining and machine learning. Among others, a foundational notation is group fairness. The vast majority of the existing works on group fairness, with a few exceptions, primarily focus on debiasing with respect to a single sensitive attribute, despite the fact that the co-existence of multiple sensitive attributes (e.g., gender, race, marital status, etc.) in the real-world is commonplace. As such, methods that can ensure a fair learning outcome with respect to all sensitive attributes of concern simultaneously need to be developed. In this paper, we study the problem of information-theoretic intersectional fairness (InfoFair), where statistical parity, a representative group fairness measure, is guaranteed among demographic groups formed by multiple sensitive attributes of interest. We formulate it as a mutual information minimization problem and propose a generic end-to-end algorithmic framework to solve it. The key idea is to leverage a variational representation of mutual information, which considers the variational distribution between learning outcomes and sensitive attributes, as well as the density ratio between the variational and the original distributions. Our proposed framework is generalizable to many different settings, including other statistical notions of fairness, and could handle any type of learning task equipped with a gradientbased optimizer. Empirical evaluations in the fair classification task on three real-world datasets demonstrate that our proposed framework can effectively debias the classification results with minimal impact to the classification accuracy.more » « less
-
Intersectionality is a framework that analyzes how interlocking systems of power and oppression affect individuals along overlapping dimensions including race, gender, sexual orientation, class, and disability. Intersectionality theory therefore implies it is important that fairness in artificial intelligence systems be protected with regard to multi-dimensional protected attributes. However, the measurement of fairness becomes statistically challenging in the multi-dimensional setting due to data sparsity, which increases rapidly in the number of dimensions, and in the values per dimension. We present a Bayesian probabilistic modeling approach for the reliable, data-efficient estimation of fairness with multidimensional protected attributes, which we apply to two existing intersectional fairness metrics. Experimental results on census data and the COMPAS criminal justice recidivism dataset demonstrate the utility of our methodology, and show that Bayesian methods are valuable for the modeling and measurement of fairness in intersectional contexts.more » « less
-
null (Ed.)Graph mining is an essential component of recommender systems and search engines. Outputs of graph mining models typically provide a ranked list sorted by each item's relevance or utility. However, recent research has identified issues of algorithmic bias in such models, and new graph mining algorithms have been proposed to correct for bias. As such, algorithm developers need tools that can help them uncover potential biases in their models while also exploring the impacts of correcting for biases when employing fairness-aware algorithms. In this paper, we present FairRankVis, a visual analytics framework designed to enable the exploration of multi-class bias in graph mining algorithms. We support both group and individual fairness levels of comparison. Our framework is designed to enable model developers to compare multi-class fairness between algorithms (for example, comparing PageRank with a debiased PageRank algorithm) to assess the impacts of algorithmic debiasing with respect to group and individual fairness. We demonstrate our framework through two usage scenarios inspecting algorithmic fairness.more » « less
-
We propose differential fairness, a multi-attribute definition of fairness in machine learning which is informed by intersectionality, a critical lens arising from the humanities literature, leveraging connections between differential privacy and legal notions of fairness. We show that our criterion behaves sensibly for any subset of the set of protected attributes, and we prove economic, privacy, and generalization guarantees. We provide a learning algorithm which respects our differential fairness criterion. Experiments on the COMPAS criminal recidivism dataset and census data demonstrate the utility of our methods.more » « less
