5G LDPC Linear Transformer for Channel Decoding

• URL: http://arxiv.org/abs/2501.14102v1
• Date: Thu, 23 Jan 2025 21:29:30 GMT
• Title: 5G LDPC Linear Transformer for Channel Decoding
• Authors: Mario Hernandez, Fernando Pinero,
• Abstract summary: This work introduces a novel, fully differentiable linear-time complexity transformer decoder and a transformer decoder to correct 5G New Radio (NR) LDPC.<n>We propose a scalable approach to decode linear block codes with $O(n)$ complexity rather than $O(n2)$ for regular transformers.<n>We achieve bit error rate performance that matches a regular Transformer decoder and surpases one iteration BP, also achieving competitive time performance against BP, even for larger block codes.
• Score: 44.99833362998488
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This work introduces a novel, fully differentiable linear-time complexity transformer decoder and a transformer decoder to correct 5G New Radio (NR) LDPC. We propose a scalable approach to decode linear block codes with $O(n)$ complexity rather than $O(n^2)$ for regular transformers. The architectures' performances are compared to Belief Propagation (BP), the production-level decoding algorithm used for 5G New Radio (NR) LDPC codes. We achieve bit error rate performance that matches a regular Transformer decoder and surpases one iteration BP, also achieving competitive time performance against BP, even for larger block codes. We utilize Sionna, Nvidia's 5G & 6G physical layer research software, for reproducible results.

Related papers

• Machine Learning Decoding of Circuit-Level Noise for Bivariate Bicycle Codes [0.42542143904778074]
  We present a recurrent, transformer-based neural network designed to decode circuit-level noise on Bi Bicycle (BB) codes. For the $[[72,12,6]]$ BB code, at a physical error rate of $p=0.1%$, our model achieves a logical error rate almost $5$ times lower than belief propagation. These results demonstrate that machine learning decoders can out-perform conventional decoders on QLDPC codes.
  arXiv  Detail & Related papers  (2025-04-17T15:57:16Z)
• Unified Error Correction Code Transformer with Low Complexity [41.04310848437611]
  Traditional decoders require dedicated hardware for each code, leading to high hardware costs.<n>We propose a unified Transformer-based decoder that handles multiple linear block codes within a single framework.
  arXiv  Detail & Related papers  (2024-10-04T12:30:42Z)
• Efficient Encoder-Decoder Transformer Decoding for Decomposable Tasks [53.550782959908524]
  We introduce a new configuration for encoder-decoder models that improves efficiency on structured output and decomposable tasks. Our method, prompt-in-decoder (PiD), encodes the input once and decodes the output in parallel, boosting both training and inference efficiency.
  arXiv  Detail & Related papers  (2024-03-19T19:27:23Z)
• Graph Neural Networks for Enhanced Decoding of Quantum LDPC Codes [6.175503577352742]
  We propose a differentiable iterative decoder for quantum low-density parity-check (LDPC) codes. The proposed algorithm is composed of classical belief propagation (BP) decoding stages and intermediate graph neural network (GNN) layers.
  arXiv  Detail & Related papers  (2023-10-26T19:56:25Z)
• Scalable Quantum Error Correction for Surface Codes using FPGA [67.74017895815125]
  A fault-tolerant quantum computer must decode and correct errors faster than they appear. We report a distributed version of the Union-Find decoder that exploits parallel computing resources for further speedup. The implementation employs a scalable architecture called Helios that organizes parallel computing resources into a hybrid tree-grid structure.
  arXiv  Detail & Related papers  (2023-01-20T04:23:00Z)
• Neural Belief Propagation Decoding of Quantum LDPC Codes Using Overcomplete Check Matrices [60.02503434201552]
  We propose to decode QLDPC codes based on a check matrix with redundant rows, generated from linear combinations of the rows in the original check matrix. This approach yields a significant improvement in decoding performance with the additional advantage of very low decoding latency.
  arXiv  Detail & Related papers  (2022-12-20T13:41:27Z)
• Graph Neural Networks for Channel Decoding [71.15576353630667]
  We showcase competitive decoding performance for various coding schemes, such as low-density parity-check (LDPC) and BCH codes. The idea is to let a neural network (NN) learn a generalized message passing algorithm over a given graph. We benchmark our proposed decoder against state-of-the-art in conventional channel decoding as well as against recent deep learning-based results.
  arXiv  Detail & Related papers  (2022-07-29T15:29:18Z)
• Error Correction Code Transformer [92.10654749898927]
  We propose to extend for the first time the Transformer architecture to the soft decoding of linear codes at arbitrary block lengths. We encode each channel's output dimension to high dimension for better representation of the bits information to be processed separately. The proposed approach demonstrates the extreme power and flexibility of Transformers and outperforms existing state-of-the-art neural decoders by large margins at a fraction of their time complexity.
  arXiv  Detail & Related papers  (2022-03-27T15:25:58Z)
• Instantaneous Grammatical Error Correction with Shallow Aggressive Decoding [57.08875260900373]
  We propose Shallow Aggressive Decoding (SAD) to improve the online inference efficiency of the Transformer for instantaneous Grammatical Error Correction (GEC) SAD aggressively decodes as many tokens as possible in parallel instead of always decoding only one token in each step to improve computational parallelism. Experiments in both English and Chinese GEC benchmarks show that aggressive decoding could yield the same predictions but with a significant speedup for online inference.
  arXiv  Detail & Related papers  (2021-06-09T10:30:59Z)
• Refined Belief-Propagation Decoding of Quantum Codes with Scalar Messages [4.340338299803562]
  Codes based on sparse matrices have good performance and can be efficiently decoded by belief-propagation (BP) BP decoding of stabilizer codes suffers a performance loss from the short cycles in the underlying Tanner graph. We show that running BP with message normalization according to a serial schedule may significantly improve the decoding performance and error-floor in computer simulation.
  arXiv  Detail & Related papers  (2021-02-14T10:29:58Z)
• Decoding 5G-NR Communications via Deep Learning [6.09170287691728]
  We propose to use Autoencoding Neural Networks (ANN) jointly with a Deep Neural Network (DNN) to construct Autoencoding Deep Neural Networks (ADNN) for demapping and decoding. Results will unveil that, for a particular BER target, $3$ dB less of Signal to Noise Ratio (SNR) is required, in Additive White Gaussian Noise (AWGN) channels.
  arXiv  Detail & Related papers  (2020-07-15T12:00:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.