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
DSAP: Analyzing Bias Through Demographic Comparison of Datasets
TL;DR: This work proposes DSAP (Demographic Similarity from Auxiliary Profiles), a two-step methodology for comparing the demographic composition of two datasets, and considers the Facial Expression Recognition task, where demographic bias has previously been found.
Proceedings Article
Learning fair representation with a parametric integral probability metric
Dongha Kim,Kunwoong Kim,Insung Kong,Ilsang Ohn,Yongdae Kim +4 more
- 07 Feb 2022
TL;DR: A new adversarial training scheme for LFR, where the integral probability metric (IPM) with a parametric family of discriminators is used and the most notable result of the proposed LFR algorithm is its theoretical guarantee about the fairness of the prediction model, which has not been considered yet.
The Model Card Authoring Toolkit: Toward Community-centered, Deliberation-driven AI Design
Hong Shen,Leijie Wang,Wesley Deng,Ciell Brusse,Ronald Velgersdijk,Haiyi Zhu +5 more
- 20 Jun 2022
TL;DR: This paper presents the Model Card Authoring Toolkit, a toolkit that supports community members to understand, navigate and negotiate a spectrum of machine learning models via deliberation and pick the ones that best align with their collective values.
Root Cause Analysis of Outliers with Missing Structural Knowledge
Nastaran Okati,Sergio Hernan Garrido Mejia,William R. Orchard,Patrick Blöbaum,Dominik Janzing +4 more
- 07 Jun 2024
TL;DR: This paper proposes simplified methods for root cause analysis of outliers, addressing challenges in existing frameworks, by leveraging causal directed acyclic graphs and anomaly scores, and providing efficient solutions for identifying unique root causes in structural causal models.
Promoting fairness in activity recognition algorithms for patient’s monitoring and evaluation systems in healthcare
Ciro Mennella,NULL AUTHOR_ID,Giuseppe De Pietro,NULL AUTHOR_ID +3 more
TL;DR: An analysis of heterogeneity in the training data is conducted to assess the impact of physical characteristics and soft-biometric attributes on activity recognition performance to quantify representation bias in multi-channel time-series activity recognition data within the healthcare domain.
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).