Massive Data Generation for Deep Learning-aided Wireless Systems Using Meta Learning and Generative Adversarial Network

TL;DR

This paper introduces a novel data generation framework combining meta learning and GANs to efficiently produce training samples for deep learning-based wireless systems, reducing the need for extensive real-world data collection.

Contribution

It proposes a new approach that leverages meta learning to enhance GANs for generating realistic wireless data, improving training efficiency and performance.

Findings

GAN-generated samples enable DL models to perform comparably to real data-trained models

Meta learning reduces the amount of real data needed for effective GAN training

Numerical results demonstrate the effectiveness of the proposed data generation method.

Abstract

As an entirely-new paradigm to design the communication systems, deep learning (DL), an approach that the machine learns the desired wireless function, has received much attention recently. In order to fully realize the benefit of DL-aided wireless system, we need to collect a large number of training samples. Unfortunately, collecting massive samples in the real environments is very challenging since it requires significant signal transmission overhead. In this paper, we propose a new type of data acquisition framework for DL-aided wireless systems. In our work, generative adversarial network (GAN) is used to generate samples approximating the real samples. To reduce the amount of training samples required for the wireless data generation, we train GAN with the help of the meta learning. From numerical experiments, we show that the DL model trained by the GAN generated samples performs close to that trained by the real samples.