Federated Linear Contextual Bandits with Heterogeneous Clients
This addresses the practical limitation of federated bandit learning in distributed systems where clients have different models, offering a solution for collaborative and private online learning.
The paper tackles the problem of federated bandit learning with heterogeneous clients, which previous works assumed were homogeneous, by introducing a clustering-based approach that achieves sub-linear regret and communication cost for all clients.
The demand for collaborative and private bandit learning across multiple agents is surging due to the growing quantity of data generated from distributed systems. Federated bandit learning has emerged as a promising framework for private, efficient, and decentralized online learning. However, almost all previous works rely on strong assumptions of client homogeneity, i.e., all participating clients shall share the same bandit model; otherwise, they all would suffer linear regret. This greatly restricts the application of federated bandit learning in practice. In this work, we introduce a new approach for federated bandits for heterogeneous clients, which clusters clients for collaborative bandit learning under the federated learning setting. Our proposed algorithm achieves non-trivial sub-linear regret and communication cost for all clients, subject to the communication protocol under federated learning that at anytime only one model can be shared by the server.