What-is and how-to for fairness in machine learning: A survey, reflection, and perspective
We review and reflect on fairness notions proposed in machine learning literature and make
an attempt to draw connections to arguments in moral and political philosophy, especially …
an attempt to draw connections to arguments in moral and political philosophy, especially …
Four years of FAccT: A reflexive, mixed-methods analysis of research contributions, shortcomings, and future prospects
Fairness, Accountability, and Transparency (FAccT) for socio-technical systems has been a
thriving area of research in recent years. An ACM conference bearing the same name has …
thriving area of research in recent years. An ACM conference bearing the same name has …
Subset selection based on multiple rankings in the presence of bias: Effectiveness of fairness constraints for multiwinner voting score functions
We consider the problem of subset selection where one is given multiple rankings of items
and the goal is to select the highest" quality" subset. Score functions from the multiwinner …
and the goal is to select the highest" quality" subset. Score functions from the multiwinner …
Maximizing submodular functions for recommendation in the presence of biases
A Mehrotra, NK Vishnoi - Proceedings of the ACM Web Conference …, 2023 - dl.acm.org
Subset selection tasks, arise in recommendation systems and search engines and ask to
select a subset of items that maximize the value for the user. The values of subsets often …
select a subset of items that maximize the value for the user. The values of subsets often …
Towards substantive conceptions of algorithmic fairness: Normative guidance from equal opportunity doctrines
F Arif Khan, E Manis, J Stoyanovich - … of the 2nd ACM Conference on …, 2022 - dl.acm.org
In this work we use Equal Opportunity (EO) doctrines from political philosophy to make
explicit the normative judgements embedded in different conceptions of algorithmic fairness …
explicit the normative judgements embedded in different conceptions of algorithmic fairness …
The long arc of fairness: Formalisations and ethical discourse
P Schwöbel, P Remmers - Proceedings of the 2022 ACM Conference on …, 2022 - dl.acm.org
In recent years, the idea of formalising and modelling fairness for algorithmic decision
making (ADM) has advanced to a point of sophisticated specialisation. However, the …
making (ADM) has advanced to a point of sophisticated specialisation. However, the …
Policy Fairness and Unknown Bias Dynamics in Sequential Allocations
This work considers a dynamic decision making framework for allocating opportunities over
time to advantaged and disadvantaged individuals, focusing on the example of college …
time to advantaged and disadvantaged individuals, focusing on the example of college …
Minimum levels of interpretability for artificial moral agents
A Vijayaraghavan, C Badea - AI and Ethics, 2024 - Springer
As artificial intelligence (AI) models continue to scale up, they are becoming more capable
and integrated into various forms of decision-making systems. For models involved in moral …
and integrated into various forms of decision-making systems. For models involved in moral …
Centralized Selection with Preferences in the Presence of Biases
This paper considers the scenario in which there are multiple institutions, each with a limited
capacity for candidates, and candidates, each with preferences over the institutions. A …
capacity for candidates, and candidates, each with preferences over the institutions. A …
Interpolating item and user fairness in recommendation systems
Online platforms employ recommendation systems to enhance customer engagement and
drive revenue. However, in a multi-sided platform where the platform interacts with diverse …
drive revenue. However, in a multi-sided platform where the platform interacts with diverse …