Deep Learning Aided Broadcast Codes with Feedback

TL;DR

This paper extends deep learning aided feedback codes to the AWGN broadcast channel, demonstrating improved performance over traditional schemes and exploring the effectiveness of RNN and MLP architectures under various conditions.

Contribution

It introduces two deep learning based broadcast coding architectures for AWGN channels and evaluates their performance in different noise regimes and training frameworks.

Findings

Deep learning codes outperform linear schemes in most cases.

Lightweight MLP-based codes excel in reliable conditions.

RNN-based codes perform better in highly unreliable scenarios.

Abstract

Deep learning aided codes have been shown to improve code performance in feedback codes in high noise regimes due to the ability to leverage non-linearity in code design. In the additive white Gaussian broadcast channel (AWGN-BC), the addition of feedback may allow the capacity region to extend far beyond the capacity region of the channel without feedback, enabling higher data rates. On the other hand, there are limited deep-learning aided implementations of broadcast codes. In this work, we extend two classes of deep-learning assisted feedback codes to the AWGN-BC channel; the first being an RNN-based architecture and the second being a lightweight MLP-based architecture. Both codes are trained using a global model, and then they are trained using a more realistic vertical federated learning based framework. We first show that in most cases, using an AWGN-BC code outperforms a linear-based concatenated scheme. Second, we show in some regimes, the lightweight architecture far exceeds the RNN-based code, but in especially unreliable conditions, the RNN-based code dominates. The results show the promise of deep-learning aided broadcast codes in unreliable channels, and future research directions are discussed.