Scalable Mamba-Based Message-Passing Neural Decoder for Error-Correcting Codes

2026-05-11

AI Summary

This work addresses the limited scalability of conventional attention-based neural decoders, which suffer from quadratic computational and memory complexity that hinders their application to long codes. To overcome this challenge, the authors propose the MMPD decoder, which for the first time integrates the Mamba state space model into neural decoding. By leveraging the local message-passing structure of Tanner graphs and eschewing dense attention mechanisms, MMPD preserves structural priors while enabling efficient long-range information propagation. The approach demonstrates significantly improved scalability: on a (1056, 880) LDPC code, it achieves a 0.45 dB gain over CrossMPT with 1.5× lower memory consumption, and its performance advantage further widens as code length increases.

Abstract

Forward error correction is essential for reliable communication over noisy channels. Attention-based model-free neural decoders have shown strong performance for short codes, but their scalability to longer codes is limited by the quadratic memory and computational cost of attention. In this paper, we introduce the Mamba message-passing decoder (MMPD), an attention-free syndrome-based neural decoder for binary linear codes. MMPD retains the Tanner-graph structure of a message-passing decoder by performing local pairwise aggregation along variable-check edges. To enable efficient long-range information propagation, these local updates are combined with bidirectional Mamba state-space blocks. By avoiding dense attention matrices, MMPD scales more favorably for long codes in both memory and computation. Experiments on the (1056, 880) LDPC code show that MMPD achieves a 0.45 dB gain over the state-of-the-art CrossMPT decoder at a specified target bit error rate, while reducing memory consumption by a factor of 1.5. This reduction factor increases substantially for longer codes, demonstrating the applicability of MMPD to scalable neural decoding of practical long codes.

Problem

• neural decoding
• error-correcting codes
• scalability
• attention mechanism
• long codes

Innovation

• Mamba
• message-passing
• neural decoder
• error-correcting codes
• state-space model