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

TL;DR

This paper introduces a new fairness framework for budgeted combinatorial multi-armed bandits using an extended Shapley value, with an algorithm that balances fairness and learning efficiency.

Contribution

It extends the Shapley value to K-Shapley for partial contributions, and proposes K-SVFair-FBF, a novel algorithm with theoretical fairness regret guarantees.

Findings

K-SVFair-FBF achieves $O(T^{3/4})$ fairness regret.

The approach effectively balances fairness and learning in experiments.

It outperforms existing baselines in federated learning and social influence tasks.

Abstract

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.