Big Data-Based Meta-Learner Generation for Fast Adaptation of Few-Shot Learning in Wireless Networks

Abstract

Driven by big data in wireless networks, the meta-learner-based scheme provides a promising paradigm to make full use of big data at the base stations to improve the per-formance of few-shot learning tasks, which plays an important role in facilitating network edge intelligence. However, it is a dilemma to balance the few-shot learning performance and the communication costs of meta-learner transmission. In this paper, we studied the fast adaptation of few-shot learning in wireless networks. First, a user grouping-based meta-learner generation scheme is designed, and a multicasting-based model transmission scheme is proposed. Second, a learning task selection scheme is designed to facilitate the fast adaptation to few-shot learning tasks at the users. Finally, the simulation results are provided to show that our proposed scheme can achieve model accuracy performance gains with low communication costs.