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
Allocating Police Resources While Limiting Racial Inequality
TL;DR: In this article, the authors attempt to reduce disproportionate minority contact by formulating a crime hot spot of crime and identifying hot spots of crime that disproportionately burden minorities via stops and arrests.
Community-in-the-loop: towards pluralistic value creation in AI, or—why AI needs business ethics
Johann Jakob Häußermann,Johann Jakob Häußermann,Christoph Lütge +2 more
- 23 Mar 2021
TL;DR: In this paper, the authors introduce a business ethics perspective based on the normative theory of contractualism and conceptualise ethical implications as conflicts between values of diverse stakeholders, arguing that such value conflicts can be resolved by an account of deliberative order ethics holding that stakeholders of an economic community deliberate the costs and benefits and agree on rules for acceptable trade-offs when AI systems are employed.
•Posted Content
ProPublica's COMPAS Data Revisited.
TL;DR: It is found that ProPublica made an important data processing mistake when it created some of the key datasets most often used by other researchers, including the datasets built to study the likelihood of recidivism within two years of the original COMPAS screening date.
39
•Posted Content
Repairing without Retraining: Avoiding Disparate Impact with Counterfactual Distributions
TL;DR: In this paper, the authors proposed to perturb the distribution of input variables for the disadvantaged groups to reduce the disparate impact of a fixed classification model over a population of interest. But, the perturbation of the distribution was performed by a black-box classifier.
39
AI and Algorithmic Bias: Source, Detection, Mitigation and Implications
TL;DR: This tutorial discusses five important aspects of algorithmic bias, including its definition and the notions of fairness policy makers, practitioners, and academic researchers have used and proposed, and methods for bias detection.
38
References
ImageNet: A large-scale hierarchical image database
Jia Deng,Wei Dong,Richard Socher,Li-Jia Li,Kai Li,Li Fei-Fei +5 more
- 20 Jun 2009
TL;DR: A new database called “ImageNet” is introduced, a large-scale ontology of images built upon the backbone of the WordNet structure, much larger in scale and diversity and much more accurate than the current image datasets.
Generative Adversarial Nets
Ian Goodfellow,Jean Pouget-Abadie,Mehdi Mirza,Bing Xu,David Warde-Farley,Sherjil Ozair,Aaron Courville,Yoshua Bengio +7 more
- 08 Dec 2014
TL;DR: A new framework for estimating generative models via an adversarial process, in which two models are simultaneously train: a generative model G that captures the data distribution and a discriminative model D that estimates the probability that a sample came from the training data rather than G.
Glove: Global Vectors for Word Representation
Jeffrey Pennington,Richard Socher,Christopher D. Manning +2 more
- 01 Oct 2014
TL;DR: A new global logbilinear regression model that combines the advantages of the two major model families in the literature: global matrix factorization and local context window methods and produces a vector space with meaningful substructure.
A Survey on Transfer Learning
Sinno Jialin Pan,Qiang Yang +1 more
TL;DR: The relationship between transfer learning and other related machine learning techniques such as domain adaptation, multitask learning and sample selection bias, as well as covariate shift are discussed.
A kernel two-sample test
TL;DR: This work proposes a framework for analyzing and comparing distributions, which is used to construct statistical tests to determine if two samples are drawn from different distributions, and presents two distribution free tests based on large deviation bounds for the maximum mean discrepancy (MMD).