Neural Window Decoder for SC-LDPC Codes

TL;DR

This paper introduces a neural window decoder for SC-LDPC codes that uses trainable weights, novel training strategies, and adaptive update scheduling to improve decoding efficiency and mitigate error propagation.

Contribution

It presents a neural window decoder with trainable weights, efficient training methods, and adaptive scheduling, advancing decoding performance for SC-LDPC codes.

Findings

Omitted 41% of check node updates without performance loss.

Effective mitigation of error propagation using a complementary weight set.

Enhanced training efficiency through targeted loss functions and active learning.

Abstract

In this paper, we propose a neural window decoder (NWD) for spatially coupled low-density parity-check (SC-LDPC) codes. The proposed NWD retains the conventional window decoder (WD) process but incorporates trainable neural weights. To train the weights of NWD, we introduce two novel training strategies. First, we restrict the loss function to target variable nodes (VNs) of the window, which prunes the neural network and accordingly enhances training efficiency. Second, we employ the active learning technique with a normalized loss term to prevent the training process from biasing toward specific training regions. Next, we develop a systematic method to derive non-uniform schedules for the NWD based on the training results. We introduce trainable damping factors that reflect the relative importance of check node (CN) updates. By skipping updates with less importance, we can omit $\mathbf{41\%}$ of CN updates without performance degradation compared to the conventional WD. Lastly, we address the error propagation problem inherent in SC-LDPC codes by deploying a complementary weight set, which is activated when an error is detected in the previous window. This adaptive decoding strategy effectively mitigates error propagation without requiring modifications to the code and decoder structures.