Disparate Impact under Title VII: An Objective Theory of Discrimination

Rutherglen, George

doi:10.2307/1072940

Cited by 37 publications

(14 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By contrast, observational measurements do not generalize beyond the narrowly defined population where the data was collected. Furthermore, by combining appropriately the contribution of different attributes, one may predict the effects both of disparate treatment [52] and disparate impact [67] on a specific population.…”

mentioning

confidence: 99%

Towards Causal Benchmarking of Bias in Face Analysis Algorithms

Balakrishnan

Xiong

Xia

et al. 2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Measuring algorithmic bias is crucial both to assess algorithmic fairness, and to guide the improvement of algorithms. Current methods to measure algorithmic bias in computer vision, which are based on observational datasets, are inadequate for this task because they conflate algorithmic bias with dataset bias.To address this problem we develop an experimental method for measuring algorithmic bias of face analysis algorithms, which manipulates directly the attributes of interest, e.g., gender and skin tone, in order to reveal causal links between attribute variation and performance change. Our proposed method is based on generating synthetic "transects" of matched sample images that are designed to differ along specific attributes while leaving other attributes constant. A crucial aspect of our approach is relying on the perception of human observers, both to guide manipulations, and to measure algorithmic bias.Besides allowing the measurement of algorithmic bias, synthetic transects have other advantages with respect to observational datasets: they sample attributes more evenly, allowing for more straightforward bias analysis on minority and intersectional groups, they enable prediction of bias in new scenarios, they greatly reduce ethical and legal challenges, and they are economical and fast to obtain, helping make bias testing affordable and widely available.We validate our method by comparing it to a study that employs the traditional observational method for analyzing bias in gender classification algorithms. The two methods reach different conclusions. While the observational method reports gender and skin color biases, the experimental method reveals biases due to gender, hair length, age, and facial hair.

show abstract

mentioning

confidence: 99%

Towards Causal Benchmarking of Bias in Face Analysis Algorithms

Balakrishnan

Xiong

Xia

et al. 2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…Group-level fairness notions are usually derived from the Disparate Impact (DI) doctrine [81] which states that no group of individuals should be adversely affected by the outcome of a decision-making system. That is, no group of individuals should be discriminated against or overtly preferred by an algorithm in terms of the output predictions made.…”

Section: A Group-level Notionsmentioning

confidence: 99%

An Overview of Fairness in Clustering

Chhabra¹,

Masalkovaite

Mohapatra

2021

IEEE Access

View full text Add to dashboard Cite

Clustering algorithms are a class of unsupervised machine learning (ML) algorithms that feature ubiquitously in modern data science, and play a key role in many learning-based application pipelines. Recently, research in the ML community has pivoted to analyzing the fairness of learning models, including clustering algorithms. Furthermore, research on fair clustering varies widely depending on the choice of clustering algorithm, fairness definitions employed, and other assumptions made regarding models. Despite this, a comprehensive survey of the field does not exist. In this paper, we seek to bridge this gap by categorizing existing research on fair clustering, and discussing possible avenues for future work. Through this survey, we aim to provide researchers with an organized overview of the field, and motivate new and unexplored lines of research regarding fairness in clustering.

show abstract

“…In the following, we discuss several group-fair social objectives that model some form equity. We invoke the legal notions of disparate treatment Barocas and Selbst [2016], Zimmer [1996] and dis-parate impact Barocas and Selbst [2016], Rutherglen [1987] and recent studies in optimization problems Tsang et al [2019], Celis et al [2018] to derive the following fairness objectives.…”

Section: Group-fair Facility Location Problemsmentioning

confidence: 99%

“…Legal definitions of discrimination, such as disparate treatment Barocas and Selbst [2016], Zimmer [1996] and disparate impact Barocas and Selbst [2016], Rutherglen [1987], 1 and recent social right movements (e.g., Black Lives Matter) have demonstrated the importance of group fairness in various settings. Ensuring group fairness in terms of equality or equity among groups of individuals in our society is desirable for many domains such as voting (see e.g., Endriss [2017], Bredereck et al [2018]), fair division (see e.g., Conitzer et al [2019], Fain et al [2018], Segal-Halevi and Suksompong [2018], Todo et al [2011], Barman et al [2018], Suksompong 1 Disparate treatment and disparate impact are two main legal definitions of discrimination describing situations where an individual is intentionally discriminated or treated differently based on the individual's classification in a protected group and a policy is affecting certain or indirectly discriminating individuals in a key group comparing to other individuals, respectively.…”

Section: Introductionmentioning

confidence: 99%

Strategyproof Mechanisms For Group-Fair Facility Location Problems

Zhou¹,

Li²,

Chan³

2021

Preprint

View full text Add to dashboard Cite

Motivated by the societal need to provide fair accessibility or representation among groups of agents, we study the group-fair facility location problems where agents are divided into groups based on criteria such as race, gender, or age. The agents are located on a real line, modeling agents' private ideal preferences/points for the facility's location (e.g., a public school or representative). Our aim is to design mechanisms to locate a facility to (approximately) minimize the costs of groups of agents to the facility fairly while eliciting the agents' private locations truthfully. We first introduce various well-motivated group-fair cost objectives and show that many natural objectives have an unbounded approximation ratio. We then consider the objectives of minimizing the maximum total group cost and minimizing the average group cost. For the first objective, we show that the approximation ratio of the median mechanism depends on the number of groups and provide a new group-based mechanism with an approximation ratio of 3. For the second objective, the median mechanism obtains a ratio of 3, and we propose a randomized mechanism that obtains a better approximation ratio. We also provide lower bounds for both objectives. We then study the notion of intergroup and intragroup fairness that measures fairness between groups and within each group. We consider various objectives and provide mechanisms with tight approximation ratios.Preprint. Under review.

show abstract

Disparate Impact under Title VII: An Objective Theory of Discrimination

Cited by 37 publications

References 0 publications

Towards Causal Benchmarking of Bias in Face Analysis Algorithms

Towards Causal Benchmarking of Bias in Face Analysis Algorithms

An Overview of Fairness in Clustering

Strategyproof Mechanisms For Group-Fair Facility Location Problems

Contact Info

Product

Resources

About