Differentially Private Federated Combinatorial Bandits with Constraints

TL;DR

This paper introduces P-FCB, a privacy-preserving federated combinatorial bandit algorithm that balances communication, regret minimization, and differential privacy in competitive online learning environments.

Contribution

It proposes a novel federated combinatorial bandit algorithm that maintains privacy and quality constraints, addressing the trade-off between privacy and regret.

Findings

P-FCB improves regret while ensuring privacy.

Communication reduces regret in federated settings.

The algorithm balances privacy, communication, and learning quality.

Abstract

There is a rapid increase in the cooperative learning paradigm in online learning settings, i.e., federated learning (FL). Unlike most FL settings, there are many situations where the agents are competitive. Each agent would like to learn from others, but the part of the information it shares for others to learn from could be sensitive; thus, it desires its privacy. This work investigates a group of agents working concurrently to solve similar combinatorial bandit problems while maintaining quality constraints. Can these agents collectively learn while keeping their sensitive information confidential by employing differential privacy? We observe that communicating can reduce the regret. However, differential privacy techniques for protecting sensitive information makes the data noisy and may deteriorate than help to improve regret. Hence, we note that it is essential to decide when to communicate and what shared data to learn to strike a functional balance between regret and privacy. For such a federated combinatorial MAB setting, we propose a Privacy-preserving Federated Combinatorial Bandit algorithm, P-FCB. We illustrate the efficacy of P-FCB through simulations. We further show that our algorithm provides an improvement in terms of regret while upholding quality threshold and meaningful privacy guarantees.