# Active Learning for Fair and Stable Online Allocations

arXiv: https://arxiv.org/abs/2406.14784 · HTML: https://mlsanity.com/paper/2406.14784/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 7 references that are in the map.
- First posted on arXiv 20 Jun 2024.

## Builds on (most cited first, 6 of 6)

- [Competing Bandits in Matching Markets](https://mlsanity.com/paper/1906.05363/) (2019)
- [Online Fair Division: analysing a Food Bank problem](https://mlsanity.com/paper/1502.07571/) (2015)
- [Regret, stability & fairness in matching markets with bandit learners](https://mlsanity.com/paper/2102.06246/) (2021)
- [Online Fair Division: A Survey](https://mlsanity.com/paper/1911.09488/) (2019)
- [My Fair Bandit: Distributed Learning of Max-Min Fairness with Multi-player Bandits](https://mlsanity.com/paper/2002.09808/) (2020)
- [Learning Fair Division from Bandit Feedback](https://mlsanity.com/paper/2311.09068/) (2023)

## Built on by (most cited first, 3 of 3)

- [Keep Everyone Happy: Online Fair Division of Numerous Items with Few Copies](https://mlsanity.com/paper/2408.12845/) (2024)
- [Envy-Free Allocation of Indivisible Goods via Noisy Queries](https://mlsanity.com/paper/2602.06361/) (2026)
- [Fair Policy Optimization in Major-Minor Weakly Coupled Markov Decision Processes](https://mlsanity.com/paper/2609.36174/) (2026)

## Abstract (arXiv)

We explore an active learning approach for dynamic fair resource allocation problems. Unlike previous work that assumes full feedback from all agents on their allocations, we consider feedback from a select subset of agents at each epoch of the online resource allocation process. Despite this restriction, our proposed algorithms provide regret bounds that are sub-linear in number of time-periods for various measures that include fairness metrics commonly used in resource allocation problems and stability considerations in matching mechanisms. The key insight of our algorithms lies in adaptively identifying the most informative feedback using dueling upper and lower confidence bounds. With this strategy, we show that efficient decision-making does not require extensive feedback and produces efficient outcomes for a variety of problem classes.