Deep Learning-based Polar Code Design

TL;DR

This paper presents a novel deep learning-based method for polar code construction that optimizes code design by integrating the decoder into the learning process, resulting in improved performance over existing schemes.

Contribution

It introduces a neural network approach to polar code design that incorporates decoding considerations and handles various constraints through gradient-based learning.

Findings

Significant performance improvements over state-of-the-art methods.

Effective handling of different channel conditions like AWGN and Rayleigh fading.

Demonstrates the feasibility of neural network-based polar code construction.

Abstract

In this work, we introduce a deep learning-based polar code construction algorithm. The core idea is to represent the information/frozen bit indices of a polar code as a binary vector which can be interpreted as trainable weights of a neural network (NN). For this, we demonstrate how this binary vector can be relaxed to a soft-valued vector, facilitating the learning process through gradient descent and enabling an efficient code construction. We further show how different polar code design constraints (e.g., code rate) can be taken into account by means of careful binary-to-soft and soft-to-binary conversions, along with rate-adjustment after each learning iteration. Besides its conceptual simplicity, this approach benefits from having the "decoder-in-the-loop", i.e., the nature of the decoder is inherently taken into consideration while learning (designing) the polar code. We show results for belief propagation (BP) decoding over both AWGN and Rayleigh fading channels with considerable performance gains over state-of-the-art construction schemes.