$\mathcal {O}^{2}$-UCB: A Federated Multi-Armed Bandit Mechanism in Zero Client-Owned Data Network
Abstract
The Federated Multi-Armed Bandit (FMAB) framework is proposed to facilitate collaborative model training in cloud-edge environments. Most existing FMAB-based systems assume that participants have personal datasets. This assumption becomes biased in scenarios with limited local data or when the discrepancy between historical data and online data cannot be quantified. Consequently, participants must passively collect data by offering services and gathering feedback from users within their charging areas. In addition, due to the mobility of the users, the number of requests is not stable. In such scenarios, effective model training requires addressing two key challenges. First, the allocation of resources for data collection at the edge is often mismatched with the actual number of service requests, resulting in limited training data and wasted resources. Second, in areas with sparse service requests, the lack of data further delays model adaptation. In this article, networks with these challenges are summarized as the training while collecting data federated bandit (TCF-bandit), and the over-area over-period upper confidence bound (<inline-formula><tex-math notation="LaTeX">$\mathcal {O}^{2}$</tex-math><alternatives><mml:math><mml:msup><mml:mi mathvariant="script">O</mml:mi><mml:mn>2</mml:mn></mml:msup></mml:math><inline-graphic xlink:href="xu-ieq2-3697698.gif"/></alternatives></inline-formula>-UCB) algorithm is proposed to address two challenges. In the <inline-formula><tex-math notation="LaTeX">$\mathcal {O}^{2}$</tex-math><alternatives><mml:math><mml:msup><mml:mi mathvariant="script">O</mml:mi><mml:mn>2</mml:mn></mml:msup></mml:math><inline-graphic xlink:href="xu-ieq3-3697698.gif"/></alternatives></inline-formula>-UCB algorithm, the cloud records request-generation patterns to mitigate resource waste caused by allocation mismatches resulting from unpredictable user mobility. Additionally, a weight-based global confidence radius is computed to assist areas with limited data in quickly identifying their optimal arms. Finally, we prove that the resource allocation waste and regret of the <inline-formula><tex-math notation="LaTeX">$\mathcal {O}^{2}$</tex-math><alternatives><mml:math><mml:msup><mml:mi mathvariant="script">O</mml:mi><mml:mn>2</mml:mn></mml:msup></mml:math><inline-graphic xlink:href="xu-ieq4-3697698.gif"/></alternatives></inline-formula>-UCB algorithm exhibit sub-linear growth. We conduct experiments in different scenarios on the MovieLens, CIFAR-10, and CIFAR-100 datasets to illustrate its superiority over SOTA methods by around 16.2%.
