TransCoder: A Neural-Enhancement Framework for Channel Codes

TL;DR

TransCoder tackles the practical challenge of deploying neural decoders by augmenting existing error-correcting codes with a modular, transformer-based neural framework that can operate at the transmitter, receiver, or both. It uses a block-attention mechanism to keep complexity low while enabling iterative refinement of channel outputs, achieving significant BLER improvements across LDPC, BCH, Polar, and Turbo codes, especially for longer block lengths and lower rates. The approach preserves the underlying code structure, bridges conventional decoding with neural processing, and demonstrates competitive performance with substantially reduced computational requirements compared to state-of-the-art neural decoders. This work offers a practical path toward neural-assisted communication suitable for resource-constrained wireless devices and real-world deployments.

Abstract

Reliable communication over noisy channels requires the design of specialized error-correcting codes (ECCs) tailored to specific system requirements. Recently, neural network-based decoders have emerged as promising tools for enhancing ECC reliability, yet their high computational complexity prevents their potential practical deployment. In this paper, we take a different approach and design a neural transmission scheme that employs the transformer architecture in order to improve the reliability of existing ECCs. We call this approach TransCoder, alluding both to its function and architecture. TransCoder operates as a code-adaptive neural module aimed at performance enhancement that can be implemented flexibly at either the transmitter, receiver, or both. The framework employs an iterative decoding procedure, where both noisy information from the channel and updates from the conventional ECC decoder are processed by a neural decoder block, utilizing a block attention mechanism for efficiency. Through extensive simulations with various conventional codes (LDPC, BCH, Polar, and Turbo) and across a wide range of channel conditions, we demonstrate that TransCoder significantly improves block error rate (BLER) performance while maintaining computational complexity comparable to traditional decoders. Notably, our approach is particularly effective for longer codes (block length >64) and at lower code rates, scenarios in which existing neural decoders often struggle (despite their formidable computational complexity). The results establish TransCoder as a promising practical solution for reliable communication among resource-constrained wireless devices.

Figures (3)

• Figure 1: Overview of the TransCoder-based communication paradigm.
• Figure 2: Normalized pairwise distances distribution between modulated codewords.
• Figure 3: Performance as $-\ln(BLER)$ vs. complexity as number of multiplications or additions for LDPC code $(121, 60)$ at $5$ dB.