Variable-Length Feedback Codes via Deep Learning

TL;DR

This paper proposes DeepVLF, a deep learning-based variable-length feedback coding scheme that improves communication reliability and performance in feedback channels by adaptively decoding message segments.

Contribution

Introduction of DeepVLF, a novel DL-aided variable-length feedback coding scheme with threshold-based decoding for enhanced adaptability and performance.

Findings

DeepVLF outperforms existing DL-based feedback codes.

Establishes a new benchmark in feedback channel coding.

Improves reliability in finite block length scenarios.

Abstract

Variable-length feedback coding has the potential to significantly enhance communication reliability in finite block length scenarios by adapting coding strategies based on real-time receiver feedback. Designing such codes, however, is challenging. While deep learning (DL) has been employed to design sophisticated feedback codes, existing DL-aided feedback codes are predominantly fixed-length and suffer performance degradation in the high code rate regime, limiting their adaptability and efficiency. This paper introduces deep variable-length feedback (DeepVLF) code, a novel DL-aided variable-length feedback coding scheme. By segmenting messages into multiple bit groups and employing a threshold-based decoding mechanism for independent decoding of each bit group across successive communication rounds, DeepVLF outperforms existing DL-based feedback codes and establishes a new benchmark in feedback channel coding.