Data Augmentation for Deep Receivers

TL;DR

This paper introduces specialized data augmentation techniques for training deep neural network-based digital receivers, enabling effective learning from limited pilot data by synthesizing reliable, diverse training samples that reflect the communication domain's characteristics.

Contribution

It proposes novel augmentation schemes tailored for digital communication data, leveraging constellation geometry and channel history to enhance deep receiver training with small datasets.

Findings

Augmentation improves deep receiver performance with limited data.

Geometric and channel-aware augmentations increase data diversity.

Enhanced training leads to more reliable digital communication reception.

Abstract

Deep neural networks (DNNs) allow digital receivers to learn to operate in complex environments. To do so, DNNs should preferably be trained using large labeled data sets with a similar statistical relationship as the one under which they are to infer. For DNN-aided receivers, obtaining labeled data conventionally involves pilot signalling at the cost of reduced spectral efficiency, typically resulting in access to limited data sets. In this paper, we study how one can enrich a small set of labeled pilots data into a larger data set for training deep receivers. Motivated by the widespread use of data augmentation techniques for enriching visual and text data, we propose dedicated augmentation schemes that exploits the characteristics of digital communication data. We identify the key considerations in data augmentations for deep receivers as the need for domain orientation, class (constellation) diversity, and low complexity. Following these guidelines, we devise three complementing augmentations that exploit the geometric properties of digital constellations. Our combined augmentation approach builds on the merits of these different augmentations to synthesize reliable data from a momentary channel distribution, to be used for training deep receivers. Furthermore, we exploit previous channel realizations to increase the reliability of the augmented samples.