New Environment Adaptation with Few Shots for OFDM Receiver and mmWave Beamforming

TL;DR

This paper introduces two few-shot learning frameworks tailored for wireless transceiver design, enabling rapid adaptation of OFDM receivers and mmWave beamforming with limited data, outperforming existing methods.

Contribution

The paper presents novel FSL frameworks based on optimization algorithms for wireless transceiver adaptation, specifically applied to OFDM receivers and mmWave beamforming.

Findings

Frameworks outperform transfer learning and meta-learning.

Effective adaptation with limited training data.

Numerical experiments confirm desirable performance.

Abstract

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.