Deep Learning-Based Polar Code Design

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.

Multi-Kernel Polar Codes versus Classical Designs with Different Rate-Matching Approaches

“…Soft decoding techniques such as belief propagation (BP) have also been developed for polar codes. Recently, some interesting polar code construction techniques have been proposed, such as using the information bottleneck method (shown in [27]) or deep learning (shown in [28]). Additionally, some efficient simulation methods to analyze polar codes performance via importance-sampling techniques exist, such as those provided in [29,30].…”

Reinforcement Learning for Bit-Flipping Decoding of Polar Codes

“…For a deep learning technique, some authors in [ 18 , 19 , 20 , 21 , 22 ] used deep learning algorithms to assist in the coding and decoding of polar codes. To enhance the coding of the polar codes, a polar code construction algorithm based on deep learning was proposed [ 18 ], which has better performance than 5G polar codes without CRC [ 19 ]. Its core idea is that the bits of polar codes are regarded as the trainable weights of the neural network.…”

Protograph-Based Design for QC Polar Codes

“…Polar codes [16]- [41] have drawn much attention as alternative capacity-approaching codes in place of LDPC codes for short block lengths, in particular for the fifth-generation (5G) networks. Besides encoder design methods [23]- [28], a number of decoder algorithms were developed [29]- [31]. With successive cancellation list (SCL) decoding [19], polar codes can be highly competitive with state-of-the-art LDPC codes.…”

“…, N } that correspond to the information bit and frozen bit locations, respectively. The lowest reliability can be selected to be in K for frozen bits, e.g., by Bhattacharyya parameter [16], density evolution [23], [24], Gaussian approximation [25], beta expansion [26], genetic algorithm [27], and deep learning [28].…”