arXiv research

Fairness measures fail in predictive settings that intentionally shift outcomes.

Advocates focusing on utility functions to avoid unfair outcomes.

Black-box explanation is the problem of explaining how a machine learning model -- whose internal logic is hidden to the auditor and generally complex -- produces its outcomes. Current approaches for solving this problem include model explanation, outcome explanation as well as model inspection. While these techniques …

Discrimination via algorithmic decision making has received considerable attention. Prior work largely focuses on defining conditions for fairness, but does not define satisfactory measures of algorithmic unfairness. In this paper, we focus on the following question: Given two unfair algorithms, how should we determine…

The paper critiques ε-fairness, showing it can lead to unfair outcomes and proposes a utility-based approach.

Local discovery method uncovers direct unfairness in complex systems.

Paper addresses fairness issues in error-prone outcomes.

The adoption of automated, data-driven decision making in an ever expanding range of applications has raised concerns about its potential unfairness towards certain social groups. In this context, a number of recent studies have focused on defining, detecting, and removing unfairness from data-driven decision systems. …

Paper uses conformal prediction sets to make criminal justice risk assessments fairer.

Systematic discriminatory biases present in our society influence the way data is collected and stored, the way variables are defined, and the way scientific findings are put into practice as policy. Automated decision procedures and learning algorithms applied to such data may serve to perpetuate existing injustice or…

Decision support systems (e.g., for ecological conservation) and autonomous systems (e.g., adaptive controllers in smart cities) start to be deployed in real applications. Although their operations often impact many users or stakeholders, no fairness consideration is generally taken into account in their design, which …

We offer a graphical interpretation of unfairness in a dataset as the presence of an unfair causal path in the causal Bayesian network representing the data-generation mechanism. We use this viewpoint to revisit the recent debate surrounding the COMPAS pretrial risk assessment tool and, more generally, to point out tha…

Despite the high interest for Machine Learning (ML) in academia and industry, many issues related to the application of ML to real-life problems are yet to be addressed. Here we put forward one limitation which arises from a lack of adaptation of ML models and datasets to specific applications. We formalise a new notio…

Develops tools to audit ML models for bias and unfairness.

Optimal LDP mechanisms reduce data unfairness in classification.

Conformal prediction sets can lead to unfair outcomes.

This study simulates biases in classifiers to assess fairness.

In this paper, we advocate for representation learning as the key to mitigating unfair prediction outcomes downstream. Motivated by a scenario where learned representations are used by third parties with unknown objectives, we propose and explore adversarial representation learning as a natural method of ensuring those…

Study shows popular RL methods are inefficient due to unfair baselines.

Consider a binary decision making process where a single machine learning classifier replaces a multitude of humans. We raise questions about the resulting loss of diversity in the decision making process. We study the potential benefits of using random classifier ensembles instead of a single classifier in the context…

Proposes a fair classification model using robust optimization.

Optimal exit strategies of CPT gamblers in unfair gambles

We study fairness in collaborative-filtering recommender systems, which are sensitive to discrimination that exists in historical data. Biased data can lead collaborative-filtering methods to make unfair predictions for users from minority groups. We identify the insufficiency of existing fairness metrics and propose f…

Recent work in fairness in machine learning has proposed adjusting for fairness by equalizing accuracy metrics across groups and has also studied how datasets affected by historical prejudices may lead to unfair decision policies. We connect these lines of work and study the residual unfairness that arises when a fairn…

The paper shows how to audit fairness in decisions with hidden risk factors.

New metric MADD assesses fairness of predictive student models.

Paper defines and solves a problem in representation learning to ensure fairness with high confidence.

This work uncovers how model and data biases interact to cause unfairness in fraud detection.

Framework improves fairness in machine learning models using adversarial techniques.

New algorithm ensures fairness without sacrificing accuracy.

FADE framework improves fairness and accuracy in ensemble learning.

New method detects and prevents unfairness in few-shot regression models.

The paper explores fair predictors in supervised learning using IPMs and Kolmogorov distance.

One often finds in the literature connections between measures of fairness and measures of feature importance employed to interpret trained classifiers. However, there seems to be no study that compares fairness measures and feature importance measures. In this paper we propose ways to evaluate and compare such measure…

Building machine learning models that are fair with respect to an unprivileged group is a topical problem. Modern fairness-aware algorithms often ignore causal effects and enforce fairness through modifications applicable to only a subset of machine learning models. In this work, we propose a new definition of fairness…

New model considers unfairness complaints to ensure multiple fairness criteria.

FPFL mitigates unfairness in private federated learning.

The paper tackles fairness in data and algorithms, expanding on prior work.

New approach to fairness in machine learning through stochastic optimization.

We present a new approach for mitigating unfairness in learned classifiers. In particular, we focus on binary classification tasks over individuals from two populations, where, as our criterion for fairness, we wish to achieve similar false positive rates in both populations, and similar false negative rates in both po…

Formulates LGFO to measure fair ML systems using legal signals.

The paper proposes a method to balance fairness and prediction accuracy by adjusting data representations.

Adversarial training can lead to unfair accuracy disparities between different groups.

We consider the problem of learning fair decision systems in complex scenarios in which a sensitive attribute might affect the decision along both fair and unfair pathways. We introduce a causal approach to disregard effects along unfair pathways that simplifies and generalizes previous literature. Our method corrects …

Automated data-driven decision making systems are increasingly being used to assist, or even replace humans in many settings. These systems function by learning from historical decisions, often taken by humans. In order to maximize the utility of these systems (or, classifiers), their training involves minimizing the e…

This paper examines AI and ML bias and fairness issues.

New method uses causal thinking to make AI fairer decisions.

Doubly fair dynamic pricing ensures equal prices for different groups over time.