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
Measuring, Interpreting, and Improving Fairness of Algorithms using Causal Inference and Randomized Experiments
James Enouen,Tianshu Sun,Yan Liu +2 more
TL;DR: An algorithm-agnostic framework (MIIF) to Measure, Interpret, and improve the Fairness of an algorithmic decision and develops an explainable machine learning model which accurately interprets and distills the beliefs of a blackbox algorithm.
Leveraging Class Balancing Techniques to Alleviate Algorithmic Bias for Predictive Tasks in Education
TL;DR: Through extensive analysis and evaluation, this study found that class balancing techniques, in general, tended to improve predictive fairness between different groups of students and added samples to the minority group, which can enhance the predictive accuracy of the Minority group while not negatively affecting the majority group.
Post-Processing Fairness Evaluation of Federated Models: An Unsupervised Approach in Healthcare.
Ilias Siniosoglou,Vasileios Argyriou,Panagiotis Sarigiannidis,Thomas Lagkas,Antonios Sarigiannidis,Sotirios K. Goudos,Shaohua Wan +6 more
TL;DR: In this article , a post-processing pipeline is proposed to rank the model by finding how fair they are by discovering and inspecting micro-Manifolds that cluster each neural model's latent knowledge.
A Classification of Feedback Loops and Their Relation to Biases in Automated Decision-Making Systems
TL;DR: In this paper , the authors use the language of dynamical systems theory, a branch of applied mathematics that deals with the analysis of the interconnection of systems with dynamic behaviors, to rigorously classify the different types of feedback loops in the ML-based decision-making pipeline.
Oversampling Higher-Performing Minorities During Machine Learning Model Training Reduces Adverse Impact Slightly but Also Reduces Model Accuracy
TL;DR: This paper used self-reports and interview transcripts from job applicants (N = 2,501) to train 9,702 ML models to predict screening decisions and found that removing adverse impact from training data only slightly reduced ML model adverse impact and tended to negatively affect ML model accuracy.
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).