FairBED: Incorporating Fairness into Bayesian Experimental Design
Abstract
Bayesian experimental design (BED) has traditionally focused exclusively on collecting data that is maximally informative, with little consideration of other desirable dataset characteristics, such as fairness. We therefore extend BED to target data that is both informative and fair. To this end, we introduce FairBED, which provides a formalism for the fairness of datasets themselves by measuring how compatible they are with a fair world, in which the target quantity we wish to learn about is unrelated to the sensitive attributes we want to be fair to. We then use this to construct practical fairness-aware BED objectives that maximise expected information gain about the target variables, while penalising information about sensitive attributes and/or their coupling with the target. We further extend FairBED to active learning, and show empirically that models trained on data gathered using FairBED provide improved fairness-accuracy trade-offs compared to randomly acquired data and conventional BED.
Related
- Power-posterior implicit sampling for efficient Bayesian experimental design: Application to contaminant source identification in groundwater flow
- TestBED: An Open-Source Toolkit for Bayesian Experimental Design
- Certified Bayesian optimal experimental design: from Expected Information Gain to Signal-to-Noise Ratio
- Risk-Aware Goal-Oriented Bayesian Optimal Experimental Design
- Bayesian Methods Incorporating Baseline Covariates for Borrowing Historical Control Data in Randomized Clinical Trials: A Neutral Comparison Study.
BibTeX
@misc{hedman2026fairbed,
title = {{FairBED: Incorporating Fairness into Bayesian Experimental Design}},
author = {Marcel Hedman and Emily Alger and Brieuc Lehmann and Chris Holmes and Tom Rainforth},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2606.23515},
eprint = {2606.23515},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2606.23515},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - FairBED: Incorporating Fairness into Bayesian Experimental Design
AU - Marcel Hedman
AU - Emily Alger
AU - Brieuc Lehmann
AU - Chris Holmes
AU - Tom Rainforth
PY - 2026
DA - 2026/10/18
PB - arXiv
DO - 10.48550/arxiv.2606.23515
UR - https://arxiv.org/abs/2606.23515
AB - Bayesian experimental design (BED) has traditionally focused exclusively on collecting data that is maximally informative, with little consideration of other desirable dataset characteristics, such as fairness. We therefore extend BED to target data that is both informative and fair. To this end, we introduce FairBED, which provides a formalism for the fairness of datasets themselves by measuring how compatible they are with a fair world, in which the target quantity we wish to learn about is unrelated to the sensitive attributes we want to be fair to. We then use this to construct practical fairness-aware BED objectives that maximise expected information gain about the target variables, while penalising information about sensitive attributes and/or their coupling with the target. We further extend FairBED to active learning, and show empirically that models trained on data gathered using FairBED provide improved fairness-accuracy trade-offs compared to randomly acquired data and conventional BED.
ER -