Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

Information Communication Technologies Conference (ICTC)

Artificial Noise Assisted Error Correction Code Transformer with Low Precision Input Data

Yuyang Shi, Fan Ding, Shuaicong Gong, Ming Jiang

Published May 1, 2026• 0 citations
Publisher

Abstract

Modern communication systems increasingly rely on efficient channel decoding, while constrained power and hardware make practical receiver design more challenging. Although the error correction code transformer (ECCT) shows strong full-precision decoding capability, prior studies have not resolved its performance degradation under quantized inputs or its incompatibility with the structured puncturing in 5G-LDPC codes. We propose a noise-assisted pre-module that mitigates discontinuities and introduces localized perturbations at punctured and quantized positions, enabling ECCT to operate effectively under low-precision and 5G-standardized conditions. Simulation results show that our proposed framework achieves comparable performance to NMS decoding without increasing complexity.

DOI
10.1109/ictc70246.2026.11650157

Related papers

Accelerating Error Correction Code Transformers

Matan Levy, Yoni Choukroun, Lior Wolf

Error correction codes (ECC) are crucial for ensuring reliable information transmission in communication systems. Choukroun & Wolf (2022b) recently introduced the Error Correction Code Transformer (ECCT), which has demonstrated promising performance across various transmission channels and families of codes. However, its high computational and memory demands limit its practical applications compared to traditional decoding algorithms. Achieving effective quantization of the ECCT presents significant challenges due to its inherently small architecture, since existing, very low-precision quantization techniques often lead to performance degradation in compact neural networks. In this paper, we introduce a novel acceleration method for transformer-based decoders. We first propose a ternary weight quantization method specifically designed for the ECCT, inducing a decoder with multiplication-free linear layers. We present an optimized self-attention mechanism to reduce computational complexity via codeaware multi-heads processing. Finally, we provide positional encoding via the Tanner graph eigendecomposition, enabling a richer representation of the graph connectivity. The approach not only matches or surpasses ECCT's performance but also significantly reduces energy consumption, memory footprint, and computational complexity. Our method brings transformer-based error correction closer to practical implementation in resource-constrained environments, achieving a 90% compression ratio and reducing arithmetic operation energy consumption by at least 224 times on modern hardware.

arXiv:2410.05911•Oct 8, 2024•7 citations

Deep Learning Approach for Efficient 5G LDPC Decoding in IoT

Sivarama Prasad Tera, Ravikumar Chinthaginjala, Priya Natha +2 more

The tremendous progress of 5G technology has transformed the landscape of the Internet of Things (IoT), allowing for fast data speeds, low delay, and widespread connection that is crucial for a variety of applications, including smart cities and industrial automation. In the context of 5G enabled IoT networks, colored noise introduces varying levels of interference across different frequency bands, which can significantly degrade the performance of 5G LDPC decoding. This paper presents a novel Deep learning approach for 5G channel LDPC code decoding tailored for next-generation IoT applications. The proposed method integrates an Iterative Normalized Min-Sum (NMS) algorithm with a Convolutional Neural Network (CNN) to enhance the performance of LDPC decoding in the presence of colored noise, a common interference in real-world communication channels. Through extensive simulations and analysis, our approach demonstrates a significant performance improvement, achieving a 3.8 dB enhancement at a Bit error rate of$10^{-6}$. This is achieved by accurately estimating and mitigating channel noise, thereby ensuring reliable data transmission for critical IoT applications. The findings indicate that our approach to decoding technique not only enhances error correction capabilities but also adapts to varying channel conditions, optimizing IoT network performance and efficiency. This research contributes a robust solution to the challenges posed by colored noise in 5G-enabled IoT networks, promoting the deployment of more reliable and efficient IoT systems.

IEEE Access•Jan 1, 2024•27 citations

Unified Error Correction Code Transformer With Low Complexity

Yongli Yan, Jieao Zhu, Tianyue Zheng +3 more

Channel coding is vital for reliable sixth-generation (6G) data transmission, employing diverse error correction codes for various application scenarios. Traditional decoders require dedicated hardware for each code, leading to high hardware costs. Recently, artificial intelligence (AI)-driven approaches, such as the error correction code Transformer (ECCT) and its enhanced version, the foundation error correction code Transformer (FECCT), have been proposed to reduce the hardware cost by leveraging the Transformer to decode multiple codes. However, their excessively high computational complexity ofO(N2) due to the self-attention mechanism in the Transformer limits scalability, whereNrepresents the sequence length. To reduce computational complexity, we propose a unified Transformer-based decoder that handles multiple linear block codes within a single framework. Specifically, a standardized unit is employed to align code length and code rate across different code types, while a redesigned low-rank unified attention module, with computational complexity ofO(N), is shared across various heads in the Transformer. Additionally, a sparse mask, derived from the parity-check matrix’s sparsity, is introduced to enhance the decoder’s ability to capture inherent constraints between information and parity-check bits, improving decoding accuracy and further reducing computational complexity by 86%. Extensive experimental results demonstrate that the proposed unified Transformer-based decoder outperforms existing methods and provides a high-performance, low-complexity solution for next-generation wireless communication systems.

arXiv:2410.03364•IEEE Internet of Things Journal•Jan 28, 2026•4 citations

Lowering the Error Floor of Error Correction Code Transformer

Park, Taewoo, Seong‐Joon Park, Kwak, Hee-Youl +2 more

With the success of transformer architectures across diverse applications, the error correction code transformer (ECCT) has gained significant attention for its superior decoding performance. In spite of its advantages, the error floor problem in ECCT decoding remains unexplored. We present the first investigation into this issue, revealing that ECCT encounters error floors, limiting its effectiveness in practical settings. To address this error floor problem, we adopt a hybrid decoding framework that integrates ECCT with conventional hard decision decoders. Unlike prior hybrid decoding schemes, our key contribution lies in proposing a novel loss function that explicitly takes into account the interaction between ECCT and hard decision decoders during training. The proposed loss function guides ECCT to focus on residual errors that are not corrected by the hard decision stages, effectively lowering the error floor. Simulation results confirm that the hybrid decoder trained with the proposed loss function achieves substantial performance gains over standard ECCT in both the waterfall and the error floor regions.

arXiv:2502.09065•Feb 13, 2025•3 citations

QAdapt: A Noise-Adaptive Neural Pre-Decoding Framework for Quantum Error Correction

Ran Miao, Rui Luo, Xiaohan Shan +1 more

Fault-tolerant quantum computing (FTQC) relies on quantum error correction to suppress physical errors and preserve logical information at scale. In practice, however, performance is constrained not only by physical noise but also by the latency of classical decoders processing rapidly generated syndrome data. This challenge is exacerbated by hardware noise that is strong, heterogeneous, and nonstationary, as well as by the simulation-to-hardware distribution shift that can substantially degrade fixed neural decoders. We present QAdapt, a noise-adaptive neural pre-decoding framework for surface-code quantum error correction. QAdapt captures local spatiotemporal correlations in syndrome data, sequentially adapts to evolving noise conditions while mitigating catastrophic forgetting, and forwards the residual syndrome to a conventional global decoder. Across 110 synthetic out-of-distribution noise configurations for rotated surface-code memory circuits, QAdapt consistently reduces the logical error rate relative to the neural pre-decoding baseline. On Google's Willow benchmark data, without target-domain fine-tuning, it achieves reductions of up to 5.79 percent in logical error rate and 9.32 percent in backend decoding latency on the residual syndrome. These results demonstrate that QAdapt provides a practical and decoder-compatible approach to improving the robustness and backend decoding efficiency of quantum error correction under evolving hardware noise.

cs.LGCross-listedarXiv:2607.28422•Jul 31, 2026•3 citations

Noise-Assisted List Decoding for 5G LDPC Codes

Jian Gao, Hao Wang, Kuangda Tian

Weak information signals can be detected with the assistance of stochastic perturbation, and nonlinear systems benefit from this phenomenon. Inspired by this, we propose a noise-assisted NMS list (Na-NMSL) algorithm for LDPC decoding. The algorithm consists of L independent NMS decoders, and the inputs of the NMS decoders are generated by adding artificial noise with different strengths to the received signal. When lifting size Z is small, list decoding is performed in the Na-NMSL decoder by utilizing the remaining hardware resources. Therefore, the Na-NMSL decoder enhances the decoding performance of NMS without additional hardware overhead. Simulation results show that the Na-NMSL decoder has a lower block error rate (BLER) and faster convergence than traditional NMS decoding.

IEEE Vehicular Technology Conference•Sep 1, 2022•0 citations
Modern communication systems increasingly rely on efficient channel decoding, while constrained power and hardware make practical receiver design more challenging. Although the error correction code transformer (ECCT) shows strong full-precision decoding capability, prior studies have not resolved its performance degradation under quantized inputs or its incompatibility with the structured puncturing in 5G-LDPC codes. We propose a noise-assisted pre-module that mitigates discontinuities and introduces localized perturbations at punctured and quantized positions, enabling ECCT to operate effectively under low-precision and 5G-standardized conditions. Simulation results show that our proposed framework achieves comparable performance to NMS decoding without increasing complexity.
Error correction codes (ECC) are crucial for ensuring reliable information transmission in communication systems. Choukroun & Wolf (2022b) recently introduced the Error Correction Code Transformer (ECCT), which has demonstrated promising performance across various transmission channels and families of codes. However, its high computational and memory demands limit its practical applications compared to traditional decoding algorithms. Achieving effective quantization of the ECCT presents significant challenges due to its inherently small architecture, since existing, very low-precision quantization techniques often lead to performance degradation in compact neural networks. In this paper, we introduce a novel acceleration method for transformer-based decoders. We first propose a ternary weight quantization method specifically designed for the ECCT, inducing a decoder with multiplication-free linear layers. We present an optimized self-attention mechanism to reduce computational complexity via codeaware multi-heads processing. Finally, we provide positional encoding via the Tanner graph eigendecomposition, enabling a richer representation of the graph connectivity. The approach not only matches or surpasses ECCT's performance but also significantly reduces energy consumption, memory footprint, and computational complexity. Our method brings transformer-based error correction closer to practical implementation in resource-constrained environments, achieving a 90% compression ratio and reducing arithmetic operation energy consumption by at least 224 times on modern hardware.
The tremendous progress of 5G technology has transformed the landscape of the Internet of Things (IoT), allowing for fast data speeds, low delay, and widespread connection that is crucial for a variety of applications, including smart cities and industrial automation. In the context of 5G enabled IoT networks, colored noise introduces varying levels of interference across different frequency bands, which can significantly degrade the performance of 5G LDPC decoding. This paper presents a novel Deep learning approach for 5G channel LDPC code decoding tailored for next-generation IoT applications. The proposed method integrates an Iterative Normalized Min-Sum (NMS) algorithm with a Convolutional Neural Network (CNN) to enhance the performance of LDPC decoding in the presence of colored noise, a common interference in real-world communication channels. Through extensive simulations and analysis, our approach demonstrates a significant performance improvement, achieving a 3.8 dB enhancement at a Bit error rate of10−610^{-6}10−6. This is achieved by accurately estimating and mitigating channel noise, thereby ensuring reliable data transmission for critical IoT applications. The findings indicate that our approach to decoding technique not only enhances error correction capabilities but also adapts to varying channel conditions, optimizing IoT network performance and efficiency. This research contributes a robust solution to the challenges posed by colored noise in 5G-enabled IoT networks, promoting the deployment of more reliable and efficient IoT systems.
Channel coding is vital for reliable sixth-generation (6G) data transmission, employing diverse error correction codes for various application scenarios. Traditional decoders require dedicated hardware for each code, leading to high hardware costs. Recently, artificial intelligence (AI)-driven approaches, such as the error correction code Transformer (ECCT) and its enhanced version, the foundation error correction code Transformer (FECCT), have been proposed to reduce the hardware cost by leveraging the Transformer to decode multiple codes. However, their excessively high computational complexity ofO(N2) due to the self-attention mechanism in the Transformer limits scalability, whereNrepresents the sequence length. To reduce computational complexity, we propose a unified Transformer-based decoder that handles multiple linear block codes within a single framework. Specifically, a standardized unit is employed to align code length and code rate across different code types, while a redesigned low-rank unified attention module, with computational complexity ofO(N), is shared across various heads in the Transformer. Additionally, a sparse mask, derived from the parity-check matrix’s sparsity, is introduced to enhance the decoder’s ability to capture inherent constraints between information and parity-check bits, improving decoding accuracy and further reducing computational complexity by 86%. Extensive experimental results demonstrate that the proposed unified Transformer-based decoder outperforms existing methods and provides a high-performance, low-complexity solution for next-generation wireless communication systems.
With the success of transformer architectures across diverse applications, the error correction code transformer (ECCT) has gained significant attention for its superior decoding performance. In spite of its advantages, the error floor problem in ECCT decoding remains unexplored. We present the first investigation into this issue, revealing that ECCT encounters error floors, limiting its effectiveness in practical settings. To address this error floor problem, we adopt a hybrid decoding framework that integrates ECCT with conventional hard decision decoders. Unlike prior hybrid decoding schemes, our key contribution lies in proposing a novel loss function that explicitly takes into account the interaction between ECCT and hard decision decoders during training. The proposed loss function guides ECCT to focus on residual errors that are not corrected by the hard decision stages, effectively lowering the error floor. Simulation results confirm that the hybrid decoder trained with the proposed loss function achieves substantial performance gains over standard ECCT in both the waterfall and the error floor regions.
Fault-tolerant quantum computing (FTQC) relies on quantum error correction to suppress physical errors and preserve logical information at scale. In practice, however, performance is constrained not only by physical noise but also by the latency of classical decoders processing rapidly generated syndrome data. This challenge is exacerbated by hardware noise that is strong, heterogeneous, and nonstationary, as well as by the simulation-to-hardware distribution shift that can substantially degrade fixed neural decoders. We present QAdapt, a noise-adaptive neural pre-decoding framework for surface-code quantum error correction. QAdapt captures local spatiotemporal correlations in syndrome data, sequentially adapts to evolving noise conditions while mitigating catastrophic forgetting, and forwards the residual syndrome to a conventional global decoder. Across 110 synthetic out-of-distribution noise configurations for rotated surface-code memory circuits, QAdapt consistently reduces the logical error rate relative to the neural pre-decoding baseline. On Google's Willow benchmark data, without target-domain fine-tuning, it achieves reductions of up to 5.79 percent in logical error rate and 9.32 percent in backend decoding latency on the residual syndrome. These results demonstrate that QAdapt provides a practical and decoder-compatible approach to improving the robustness and backend decoding efficiency of quantum error correction under evolving hardware noise.
Weak information signals can be detected with the assistance of stochastic perturbation, and nonlinear systems benefit from this phenomenon. Inspired by this, we propose a noise-assisted NMS list (Na-NMSL) algorithm for LDPC decoding. The algorithm consists of L independent NMS decoders, and the inputs of the NMS decoders are generated by adding artificial noise with different strengths to the received signal. When lifting size Z is small, list decoding is performed in the Na-NMSL decoder by utilizing the remaining hardware resources. Therefore, the Na-NMSL decoder enhances the decoding performance of NMS without additional hardware overhead. Simulation results show that the Na-NMSL decoder has a lower block error rate (BLER) and faster convergence than traditional NMS decoding.