Related papers: What is Proxy Discrimination?
This paper presents an approach to formalizing and enforcing a class of use privacy properties in data-driven systems. In contrast to prior work, we focus on use restrictions on proxies (i.e. strong predictors) of protected information…
Fairness assumptions are a valuable tool when reasoning about systems. In this paper, we classify several fairness properties found in the literature and argue that most of them are too restrictive for many applications. As an alternative…
Recent research has helped to cultivate growing awareness that machine learning systems fueled by big data can create or exacerbate troubling disparities in society. Much of this research comes from outside of the practicing data science…
Machine learning algorithms for prediction are increasingly being used in critical decisions affecting human lives. Various fairness formalizations, with no firm consensus yet, are employed to prevent such algorithms from systematically…
Motivated by scenarios where data is used for diverse prediction tasks, we study whether fair representation can be used to guarantee fairness for unknown tasks and for multiple fairness notions simultaneously. We consider seven group…
Many machine learning systems make extensive use of large amounts of data regarding human behaviors. Several researchers have found various discriminatory practices related to the use of human-related machine learning systems, for example…
We explore and compare a variety of definitions for privacy and disclosure limitation in statistical estimation and data analysis, including (approximate) differential privacy, testing-based definitions of privacy, and posterior guarantees…
Nowadays, many decisions are made using predictive models built on historical data.Predictive models may systematically discriminate groups of people even if the computing process is fair and well-intentioned. Discrimination-aware data…
Divergent word usages reflect differences among people. In this paper, we present a novel angle for studying word usage divergence -- word interpretations. We propose an approach that quantifies semantic differences in interpretations among…
In this work we generalize standard Decision Theory by assuming that two outcomes can also be incomparable. Two motivating scenarios show how incomparability may be helpful to represent those situations where, due to lack of information,…
Various measures can be used to estimate bias or unfairness in a predictor. Previous work has already established that some of these measures are incompatible with each other. Here we show that, when groups differ in prevalence of the…
Pronoun disambiguation in understanding text and discourse often requires the application of both general pragmatic knowledge and context-specific information. In AI and linguistics research, this has mostly been studied in cases where the…
In computational social choice, the distortion of a voting rule quantifies the degree to which the rule overcomes limited preference information to select a socially desirable outcome. This concept has been investigated extensively, but…
Algorithmic discrimination is a condition that arises when data-driven software unfairly treats users based on attributes like ethnicity, race, gender, sexual orientation, religion, age, disability, or other personal characteristics.…
Discrimination task is treated in the case of only partial prior information from measurements of unknown states. The construction of the optimal discrimination device and estimation of unknown states is performed simultaneously. A…
An online seller or platform is technically able to offer every consumer a different price for the same product, based on information it has about the customers. Such online price discrimination exacerbates concerns regarding the fairness…
Algorithmic discrimination is an important aspect when data is used for predictive purposes. This paper analyzes the relationships between discrimination and classification, data set partitioning, and decision models, as well as…
A growing effort in NLP aims to build datasets of human explanations. However, the term explanation encompasses a broad range of notions, each with different properties and ramifications. Our goal is to provide an overview of diverse types…
While much research focused on producing explanations, it is still unclear how the produced explanations' quality can be evaluated in a meaningful way. Today's predominant approach is to quantify explanations using proxy scores which…
Most research on natural language processing treats bias as an absolute concept: Based on a (probably complex) algorithmic analysis, a sentence, an article, or a text is classified as biased or not. Given the fact that for humans the…