Meritocratic Fairness in Budgeted Combinatorial Multi-armed Bandits via Shapley Values

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Sharma, Shradha, Dhamal, Swapnil, Jain, Shweta
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911638924296192
author Sharma, Shradha
Dhamal, Swapnil
Jain, Shweta
author_facet Sharma, Shradha
Dhamal, Swapnil
Jain, Shweta
contents We propose a new framework for meritocratic fairness in budgeted combinatorial multi-armed bandits with full-bandit feedback (BCMAB-FBF). Unlike semi-bandit feedback, the contribution of individual arms is not received in full-bandit feedback, making the setting significantly more challenging. To compute arm contributions in BCMAB-FBF, we first extend the Shapley value, a classical solution concept from cooperative game theory, to the $K$-Shapley value, which captures the marginal contribution of an agent restricted to a set of size at most $K$. We show that $K$-Shapley value is a unique solution concept that satisfies Symmetry, Linearity, Null player, and efficiency properties. We next propose K-SVFair-FBF, a fairness-aware bandit algorithm that adaptively estimates $K$-Shapley value with unknown valuation function. Unlike standard bandit literature on full bandit feedback, K-SVFair-FBF not only learns the valuation function under full feedback setting but also mitigates the noise arising from Monte Carlo approximations. Theoretically, we prove that K-SVFair-FBF achieves $O(T^{3/4})$ regret bound on fairness regret. Through experiments on federated learning and social influence maximization datasets, we demonstrate that our approach achieves fairness and performs more effectively than existing baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2605_00762
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Meritocratic Fairness in Budgeted Combinatorial Multi-armed Bandits via Shapley Values
Sharma, Shradha
Dhamal, Swapnil
Jain, Shweta
Machine Learning
Artificial Intelligence
Multiagent Systems
We propose a new framework for meritocratic fairness in budgeted combinatorial multi-armed bandits with full-bandit feedback (BCMAB-FBF). Unlike semi-bandit feedback, the contribution of individual arms is not received in full-bandit feedback, making the setting significantly more challenging. To compute arm contributions in BCMAB-FBF, we first extend the Shapley value, a classical solution concept from cooperative game theory, to the $K$-Shapley value, which captures the marginal contribution of an agent restricted to a set of size at most $K$. We show that $K$-Shapley value is a unique solution concept that satisfies Symmetry, Linearity, Null player, and efficiency properties. We next propose K-SVFair-FBF, a fairness-aware bandit algorithm that adaptively estimates $K$-Shapley value with unknown valuation function. Unlike standard bandit literature on full bandit feedback, K-SVFair-FBF not only learns the valuation function under full feedback setting but also mitigates the noise arising from Monte Carlo approximations. Theoretically, we prove that K-SVFair-FBF achieves $O(T^{3/4})$ regret bound on fairness regret. Through experiments on federated learning and social influence maximization datasets, we demonstrate that our approach achieves fairness and performs more effectively than existing baselines.
title Meritocratic Fairness in Budgeted Combinatorial Multi-armed Bandits via Shapley Values
topic Machine Learning
Artificial Intelligence
Multiagent Systems
url https://arxiv.org/abs/2605.00762