Algorithmic Fairness Datasets: the Story so Far

Fabris, Alessandro; Messina, Stefano; Silvello, Gianmaria; Susto, Gian Antonio

doi:10.48550/arxiv.2202.01711

Cited by 3 publications

(3 citation statements)

References 103 publications

(188 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first three years of the conference were examined to understand the process by which categories emerge and become naturalized within a nascent community of practice. To target works primarily about algorithmic fairness, the author adapted the selection criteria proposed in Fabris et al 's [10] survey of data sets used in the algorithmic fairness literature and selected the subsample of these papers whose abstract contains at least one of the following strings, where the asterisk represents the wildcard character: *fair* (targeting, for example "fairness", "unfair"), *bias* ("biased", "debias"), *discriminat* ("antidiscrimination", "discriminatory"), disparate, *parit* ("parity", "disparities"). From this subsample, only the papers that deal directly with race by restricting to papers which contain at least one of the following strings race, *racism ("racism", "antiracism"), racial were selected.…”

Section: Samplementioning

confidence: 99%

An Empirical Analysis of Racial Categories in the Algorithmic Fairness Literature

Abdu

Pasquetto

Jacobs

2023

2023 ACM Conference on Fairness, Accountability, and Transparency

View full text Add to dashboard Cite

Recent work in algorithmic fairness has highlighted the challenge of defining racial categories for the purposes of anti-discrimination. These challenges are not new but have previously fallen to the state, which enacts race through government statistics, policies, and evidentiary standards in anti-discrimination law. Drawing on the history of state race-making, we examine how longstanding questions about the nature of race and discrimination appear within the algorithmic fairness literature. Through a content analysis of 60 papers published at FAccT between 2018 and 2020, we analyze how race is conceptualized and formalized in algorithmic fairness frameworks. We note that differing notions of race are adopted inconsistently, at times even within a single analysis. We also explore the institutional influences and values associated with these choices. While we find that categories used in algorithmic fairness work often echo legal frameworks, we demonstrate that values from academic computer science play an equally important role in the construction of racial categories. Finally, we examine the reasoning behind different operationalizations of race, finding that few papers explicitly describe their choices and even fewer justify them. We argue that the construction of racial categories is a value-laden process with significant social and political consequences for the project of algorithmic fairness. The widespread lack of justification around the operationalization of race reflects institutional norms that allow these political decisions to remain obscured within the backstage of knowledge production.

show abstract

Section: Samplementioning

confidence: 99%

An Empirical Analysis of Racial Categories in the Algorithmic Fairness Literature

Abdu

Pasquetto

Jacobs

2023

2023 ACM Conference on Fairness, Accountability, and Transparency

View full text Add to dashboard Cite

show abstract

“…Indeed, they have been demonstrated to be a source of racial [31,32] or gender [33] discrimination. Moreover, well-known datasets such as CelebA [34], Open Images [35] or ImageNet [3] lack of diversity-as shown in [36] or [37]-have resulted in imbalanced samples. Thus, state-of-the-art algorithms are unable to yield uniform performance over all sub.…”

Section: Improperly Sampled Training Datamentioning

confidence: 99%

Detecting and Processing Unsuspected Sensitive Variables for Robust Machine Learning

Risser,

Picard,

Hervier

et al. 2023

Algorithms

View full text Add to dashboard Cite

The problem of algorithmic bias in machine learning has recently gained a lot of attention due to its potentially strong impact on our societies. In much the same manner, algorithmic biases can alter industrial and safety-critical machine learning applications, where high-dimensional inputs are used. This issue has, however, been mostly left out of the spotlight in the machine learning literature. Contrary to societal applications, where a set of potentially sensitive variables, such as gender or race, can be defined by common sense or by regulations to draw attention to potential risks, the sensitive variables are often unsuspected in industrial and safety-critical applications. In addition, these unsuspected sensitive variables may be indirectly represented as a latent feature of the input data. For instance, the predictions of an image classifier may be altered by reconstruction artefacts in a small subset of the training images. This raises serious and well-founded concerns about the commercial deployment of AI-based solutions, especially in a context where new regulations address bias issues in AI. The purpose of our paper is, then, to first give a large overview of recent advances in robust machine learning. Then, we propose a new procedure to detect and to treat such unknown biases. As far as we know, no equivalent procedure has been proposed in the literature so far. The procedure is also generic enough to be used in a wide variety of industrial contexts. Its relevance is demonstrated on a set of satellite images used to train a classifier. In this illustration, our technique detects that a subset of the training images has reconstruction faults, leading to systematic prediction errors that would have been unsuspected using conventional cross-validation techniques.

show abstract

“…Most existing fairness research focuses on group fairness, and it does so in the context of data types other than geospatial [13]. Individual fairness enforcement requires the evaluation of 𝑂 (𝑚 2 ) hard constraints, growing quadratically with the number of datapoints, which is more difficult to achieve efficiently.…”

Section: Experimental Evaluationmentioning

confidence: 99%

Models and Mechanisms for Fairness in Location Data Processing

Shaham¹,

Ghinita²,

Shahabi³

2022

Preprint

View full text Add to dashboard Cite

Location data use has become pervasive in the last decade due to the advent of mobile apps, as well as novel areas such as smart health, smart cities, etc. At the same time, significant concerns have surfaced with respect to fairness in data processing. Individuals from certain population segments may be unfairly treated when being considered for loan or job applications, access to public resources, or other types of services. In the case of location data, fairness is an important concern, given that an individual's whereabouts are often correlated with sensitive attributes, e.g., race, income, education.While fairness has received significant attention recently, e.g., in the case of machine learning, there is little focus on the challenges of achieving fairness when dealing with location data. Due to their characteristics and specific type of processing algorithms, location data pose important fairness challenges that must be addressed in a comprehensive and effective manner. In this paper, we adapt existing fairness models to suit the specific properties of location data and spatial processing. We focus on individual fairness, which is more difficult to achieve, and more relevant for most location data processing scenarios. First, we devise a novel building block to achieve fairness in the form of fair polynomials. Then, we propose two mechanisms based on fair polynomials that achieve individual fairness, corresponding to two common interaction types based on location data. Extensive experimental results on real data show that the proposed mechanisms achieve individual location fairness without sacrificing utility.

show abstract

Algorithmic Fairness Datasets: the Story so Far

Cited by 3 publications

References 103 publications

An Empirical Analysis of Racial Categories in the Algorithmic Fairness Literature

An Empirical Analysis of Racial Categories in the Algorithmic Fairness Literature

Detecting and Processing Unsuspected Sensitive Variables for Robust Machine Learning

Models and Mechanisms for Fairness in Location Data Processing

Contact Info

Product

Resources

About