Adaptive Data Augmentation for Deep Receivers

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. The superiority of our approach is numerically evaluated for training several deep receiver architectures in different channel conditions. We consider both linear and non-linear synthetic channels, as well as the COST 2100 channel generator, for both single-input single-output and multiple-input multiple-output scenarios. We show that our combined augmentations approach allows DNN-aided receivers to achieve gains of up to 1 dB in bit error rate and of up to ×3 in spectral efficiency, compared to regular non-augmented training. Moreover, we demonstrate that our augmentations benefit training even as the number of pilots increases, and perform an ablation study on the different augmentations, which shows that the combined approach surpasses each individual augmentation technique.

Online Meta-Learning for Hybrid Model-Based Deep Receivers

“…We compare standard training with training that leverages data augmentation. For the latter scheme, at each time step, the pilot data is enriched with 600 artificial symbols via a constellation-conserving projection and a translationpreserving transformation [12].…”

“…While data augmentation is quite common in AI, it is highly geared towards image and language data. Data augmentations for digital communications have been explored in [11], and more recently in [12]. The techniques studied in [12] include leveraging the symmetry in digital constellations to project error patterns between different symbols; exploiting the independence between the noise and the transmitted symbols to generate additional noisy realizations; and accounting for forms of invariance to constellation-preserving rotations exhibited by wireless channels.…”

“…Communication channels are dynamic, implying that the receiver task, dictated by the data distribution, changes over time. This makes the standard Data augmentation [11], [12] Training Algorithm Meta-learning [13]- [16] Bayesian learning [17], [18] Modular training [13] Fig. 1: A summary of methods surveyed in this article that adapt the three pillars of AI to the requirements of deep wireless receivers.…”

Low-Complexity Near-Optimum Symbol Detection Based on Neural Enhancement of Factor Graphs

“…n and y (d) are from a labeled data set D, which will be formally defined later in (18) in Sec. III-C.…”

“…While these data-aided receivers do not require CSI, they still rely on labeled data obtained from, e.g., pilots. Moreover, their reliance on DNNs makes their online adaptation to rapidly time-variant channels challenging in terms of efficient learning [17] and data accumulation [18], see also [19].…”