As decision‐making increasingly relies on machine learning (ML) and (big) data, the issue of fairness in data‐driven artificial intelligence systems is receiving increasing attention from …
This paper provides a comprehensive survey of bias mitigation methods for achieving fairness in Machine Learning (ML) models. We collect a total of 341 publications concerning …
Non-discrimination is a recognized objective in algorithmic decision making. In this paper, we introduce a novel probabilistic formulation of data pre-processing for reducing …
We summarize the potential impact that the European Union's new General Data Protection Regulation will have on the routine use of machine learning algorithms. Slated to take effect …
In this work, we define and solve the Fair Top-k Ranking problem, in which we want to determine a subset of k candidates from a large pool of n» k candidates, maximizing utility …
H Jiang, O Nachum - International conference on artificial …, 2020 - proceedings.mlr.press
Datasets often contain biases which unfairly disadvantage certain groups, and classifiers trained on such datasets can inherit these biases. In this paper, we provide a mathematical …
M Veale, R Binns - Big Data & Society, 2017 - journals.sagepub.com
Decisions based on algorithmic, machine learning models can be unfair, reproducing biases in historical data used to train them. While computational techniques are emerging to …
This paper defines software fairness and discrimination and develops a testing-based method for measuring if and how much software discriminates, focusing on causality in …
When it is ethical and legal to use a sensitive attribute (such as gender or race) in machine learning systems, the question remains how to do so. We show that the naive application of …