Scalable Mamba-Based Message-Passing Neural Decoder for Error-Correcting Codes
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.
Related
- Why Multi-Layer Message Passing Works: Completeness Theory for Graph Neural Network Interatomic Potentials
- Beyond Graph Diameter: Structural Determinants of Long-Range Information Propagation in Message-Passing Neural Networks
- Geometry-Aware Simplicial Message Passing
- Message-passing graph persistence
- Learned Score-Based Turbo Message Passing for Channel Recovery From Spatially Compressed Measurements
BibTeX
@misc{gusev2026scalable,
title = {{Scalable Mamba-Based Message-Passing Neural Decoder for Error-Correcting Codes}},
author = {Rostislav Gusev and Nikita Aleksandrov and Artem Solomkin and Dmitry Artemasov},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2605.10681},
eprint = {2605.10681},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2605.10681},
}
RIS
TY - UNPB
TI - Scalable Mamba-Based Message-Passing Neural Decoder for Error-Correcting Codes
AU - Rostislav Gusev
AU - Nikita Aleksandrov
AU - Artem Solomkin
AU - Dmitry Artemasov
PY - 2026
DA - 2026/09/19
PB - arXiv
DO - 10.48550/arxiv.2605.10681
UR - https://arxiv.org/abs/2605.10681
AB - 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.
ER -