How to be Fair and Diverse?
L. Elisa Celis, Amit Deshpande, Tarun Kathuria, Nisheeth K. Vishnoi

TL;DR
This paper introduces a new algorithmic framework that produces subsamples which are both fair and diverse, addressing the challenge of balancing fairness and representativeness in data sampling for machine learning.
Contribution
The paper proposes a novel framework for generating subsamples that simultaneously ensure fairness and diversity, filling a gap in existing methods that typically focus on one or the other.
Findings
Marked improvements in fairness achieved
Feature diversity maintained with minimal compromise
Effective in image summarization tasks
Abstract
Due to the recent cases of algorithmic bias in data-driven decision-making, machine learning methods are being put under the microscope in order to understand the root cause of these biases and how to correct them. Here, we consider a basic algorithmic task that is central in machine learning: subsampling from a large data set. Subsamples are used both as an end-goal in data summarization (where fairness could either be a legal, political or moral requirement) and to train algorithms (where biases in the samples are often a source of bias in the resulting model). Consequently, there is a growing effort to modify either the subsampling methods or the algorithms themselves in order to ensure fairness. However, in doing so, a question that seems to be overlooked is whether it is possible to produce fair subsamples that are also adequately representative of the feature space of the data set…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdversarial Robustness in Machine Learning · Explainable Artificial Intelligence (XAI) · Ethics and Social Impacts of AI
