Few-shot learning (FSL) enables adaptation to new tasks with only limited training data. In wireless communications, channel environments can vary drastically; therefore, FSL techniques can quickly adjust transceiver accordingly. In this paper, we develop two FSL frameworks that fit in wireless transceiver design. Both frameworks are base on optimization programs that can be solved by well-known algorithms like the inexact alternating direction method of multipliers (iADMM) and the inexact alternating direction method (iADM). As examples, we demonstrate how the proposed two FSL frameworks are used for the OFDM receiver and beamforming (BF) for the millimeter wave (mmWave) system. The numerical experiments confirm their desirable performance in both applications compared to other popular approaches, such as transfer learning (TL) and model-agnostic meta-learning.

翻译：少样本学习（FSL）能够利用有限的训练数据适应新任务。在无线通信中，信道环境可能剧烈变化，因此FSL技术可快速调整收发机。本文开发了两种适用于无线收发机设计的FSL框架。两种框架均基于可通过不精确交替方向乘子法（iADMM）和不精确交替方向法（iADM）等经典算法求解的优化问题。作为示例，我们展示所提出的两种FSL框架在OFDM接收机和毫米波（mmWave）系统波束成形（BF）中的应用。数值实验证实，与迁移学习（TL）和模型无关元学习等其他主流方法相比，所提框架在两种应用场景中均具有优越性能。