DNC-Aided SCL-Flip Decoding of Polar Codes

TL;DR

This paper introduces a neural network-assisted flip decoding algorithm for polar codes that improves performance and reduces decoding attempts by accurately identifying error bits using differentiable neural computers.

Contribution

It proposes a novel DNC-based flip decoding method with two phases for better error bit identification, enhancing polar code decoding performance.

Findings

Achieves up to 0.34dB coding gain improvement.

Reduces average decoding attempts by 54.2%.

Demonstrates effectiveness over prior flip algorithms.

Abstract

Successive-cancellation list (SCL) decoding of polar codes has been adopted for 5G. However, the performance is not very satisfactory with moderate code length. Heuristic or deep-learning-aided (DL-aided) flip algorithms have been developed to tackle this problem. The key for successful flip decoding is to accurately identify error bit positions. In this work, we propose a new flip algorithm with help of differentiable neural computer (DNC). New state and action encoding are developed for better DNC training and inference efficiency. The proposed method consists of two phases: i) a flip DNC (F-DNC) is exploited to rank most likely flip positions for multi-bit flipping; ii) if decoding still fails, a flip-validate DNC (FV-DNC) is used to re-select error bit positions for successive flip decoding trials. Supervised training methods are designed accordingly for the two DNCs. Simulation results show that proposed DNC-aided SCL-Flip (DNC-SCLF) decoding demonstrates up to 0.34dB coding gain improvement or 54.2 reduction in average number of decoding attempts compared to prior works.