For One-Shot Decoding: Self-supervised Deep Learning-Based Polar Decoder

TL;DR

This paper introduces a self-supervised deep learning method for polar code decoding that enables one-shot decoding without labeled data, achieving near-MAP performance for short packets and better generalization.

Contribution

It presents a novel self-supervised neural network decoder for polar codes that eliminates the need for labeled training data, improving practicality and performance.

Findings

BER and BLER approach MAP decoder for short packets

The NN decoder shows superior generalization ability

The method enables training directly on actual data without labels

Abstract

We propose a self-supervised deep learning-based decoding scheme that enables one-shot decoding of polar codes. In the proposed scheme, rather than using the information bit vectors as labels for training the neural network (NN) through supervised learning as the conventional scheme did, the NN is trained to function as a bounded distance decoder by leveraging the generator matrix of polar codes through self-supervised learning. This approach eliminates the reliance on predefined labels, empowering the potential to train directly on the actual data within communication systems and thereby enhancing the applicability. Furthermore, computer simulations demonstrate that (i) the bit error rate (BER) and block error rate (BLER) performances of the proposed scheme can approach those of the maximum a posteriori (MAP) decoder for very short packets and (ii) the proposed NN decoder (NND) exhibits much superior generalization ability compared to the conventional one.