Open AccessPosted Content
Algorithmic Fairness
Dana Pessach,Erez Shmueli +1 more
TL;DR: An overview of the main concepts of identifying, measuring and improving algorithmic fairness when using AI algorithms is presented and the most commonly used fairness-related datasets in this field are described.
read more
Abstract: An increasing number of decisions regarding the daily lives of human beings are being controlled by artificial intelligence (AI) algorithms in spheres ranging from healthcare, transportation, and education to college admissions, recruitment, provision of loans and many more realms. Since they now touch on many aspects of our lives, it is crucial to develop AI algorithms that are not only accurate but also objective and fair. Recent studies have shown that algorithmic decision-making may be inherently prone to unfairness, even when there is no intention for it. This paper presents an overview of the main concepts of identifying, measuring and improving algorithmic fairness when using AI algorithms. The paper begins by discussing the causes of algorithmic bias and unfairness and the common definitions and measures for fairness. Fairness-enhancing mechanisms are then reviewed and divided into pre-process, in-process and post-process mechanisms. A comprehensive comparison of the mechanisms is then conducted, towards a better understanding of which mechanisms should be used in different scenarios. The paper then describes the most commonly used fairness-related datasets in this field. Finally, the paper ends by reviewing several emerging research sub-fields of algorithmic fairness.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Figures
Table 1. Measures and Definitions for Algorithmic Fairness 
Table 4. Additional Measures and Definitions for Algorithmic Fairness 
Fig. 1. If the SAT scores were used for hiring, then unprivileged candidates with high potential would be excluded, whereas lower potential candidates from the privileged group would be hired instead 
Table 3. Common Benchmark Datasets for Algorithmic Fairness 
Table 2. Pre-Process, In-Process and Post-Process Mechanisms for Algorithmic Fairness
Citations
Artificial Intelligence in Human Resources Management: Challenges and a Path Forward:
TL;DR: There is a substantial gap between the promise and reality of artificial intelligence in human resource (HR) management, and four challenges in using data science techniques for HR management are identified.
848
•Posted Content
Fairness in Machine Learning: A Survey.
Simon Caton,Christian Haas +1 more
TL;DR: An overview of the different schools of thought and approaches to mitigating (social) biases and increase fairness in the Machine Learning literature is provided, organises approaches into the widely accepted framework of pre-processing, in- processing, and post-processing methods, subcategorizing into a further 11 method areas.
Algorithmic Fairness: Choices, Assumptions, and Definitions
TL;DR: It is shown how choices and assumptions made—often implicitly—to justify the use of prediction-based decision-making can raise fairness concerns and a notationally consistent catalog of fairness definitions from the literature is presented.
491
A Framework for Understanding Sources of Harm throughout the Machine Learning Life Cycle
Harini Suresh,John V. Guttag +1 more
- 05 Oct 2021
TL;DR: In this paper, the authors identify seven potential sources of downstream harm in machine learning, spanning data collection, development, and deployment, and propose a framework to facilitate more productive and precise communication around these issues.
417
References
•Posted Content
Learning Fair Classifiers: A Regularization-Inspired Approach.
Yahav Bechavod,Katrina Ligett +1 more
- 30 Jun 2017
TL;DR: A regularization-inspired approach for reducing bias in learned classifiers is presented and its ability to achieve both fairness and accuracy is evaluated, using the COMPAS scores data for prediction of recidivism.
FaiRecSys: mitigating algorithmic bias in recommender systems
TL;DR: This paper highlights the connection between predictability of sensitive features and bias in the results of recommendations and offers a theoretically founded bound on recommendation bias based on that connection and proposes an algorithm that mitigates algorithmic bias by post-processing the recommendation matrix with minimum impact on the utility of recommendations provided to the end-users.
Preventing Disparate Treatment in Sequential Decision Making.
Hoda Heidari,Andreas Krause +1 more
- 01 Jul 2018
TL;DR: This work proposes a general framework for post-processing predictions made by a black-box learning model, that guarantees the resulting sequence of outcomes is consistent, and shows theoretically that imposing consistency will not significantly slow down learning.
•Posted Content
Achieving Fairness through Adversarial Learning: an Application to Recidivism Prediction.
TL;DR: An adversarially-trained neural network is presented that predicts recidivism and is trained to remove racial bias and gains predictive accuracy and gets closer to achieving two out of three measures of fairness: parity and equality of odds.
Decoupled classifiers for fair and efficient machine learning
Cynthia Dwork,Nicole Immorlica,Adam Tauman Kalai,Mark D.M. Leiserson +3 more
- 20 Jul 2017
TL;DR: A simple and efficient decoupling technique is provided, which can be added on top of any black-box machine learning algorithm, to learn different classifiers for different groups.