CRC-Aided Learned Ensembles of Belief-Propagation Polar Decoders

TL;DR

This paper introduces a novel CRC-aided ensemble of neural belief-propagation decoders for polar codes, achieving improved error correction with manageable complexity and latency.

Contribution

It combines list-decoding and neural decoding in an ensemble framework using CRC for selection, a novel approach for polar code decoding.

Findings

Achieves around 0.25dB gain in frame-error rate.

Complexity approaches that of a single BP decoder at high SNR.

Provides detailed complexity and latency analysis.

Abstract

Polar codes have promising error-correction capabilities. Yet, decoding polar codes is often challenging, particularly with large blocks, with recently proposed decoders based on list-decoding or neural-decoding. The former applies multiple decoders or the same decoder multiple times with some redundancy, while the latter family utilizes emerging deep learning schemes to learn to decode from data. In this work we introduce a novel polar decoder that combines the list-decoding with neural-decoding, by forming an ensemble of multiple weighted belief-propagation (WBP) decoders, each trained to decode different data. We employ the cyclic-redundancy check (CRC) code as a proxy for combining the ensemble decoders and selecting the most-likely decoded word after inference, while facilitating real-time decoding. We evaluate our scheme over a wide range of polar codes lengths, empirically showing that gains of around 0.25dB in frame-error rate could be achieved. Moreover, we provide complexity and latency analysis, showing that the number of operations required approaches that of a single BP decoder at high signal-to-noise ratios.