aiqbench analysis
This research introduces a neural belief-matching decoder for topological quantum error correction codes that significantly reduces decoding complexity while maintaining performance through transfer learning. By employing convolutional architectures, the approach enables models trained on smaller code instances to be effectively applied to larger systems without retraining. This advancement addresses critical scalability challenges in fault-tolerant quantum computing by optimizing the interface between classical neural networks and topological error correction schemes.
Neural Belief-Matching Decoding for Topological Quantum Error Correction Codes
arXiv:2603.21730v2 Announce Type: replace Abstract: Quantum error correction (QEC) is critical for scalable fault-tolerant quantum computing. Topological codes, such as the toric code, offer hardware-efficient architectures but their Tanner graphs contain many girth-4 cycles that degrade the performance of belief-propagation (BP) decoding. For this reason, BP decoding is typically followed by a more complex second stage decoder such as minimum-weight perfect matching. These combined decoders achieve a remarkable performance, albeit at the cost of increased complexity. In this paper we propose two key improvements for the decoding of toric code. The first one is replacing the BP decoder by a neural BP decoder, giving rise to the neural belief-matching decoder which substantially decreases the average decoding complexity. The main drawback of this approach is the high cost associated with the training of the neural BP decoder. To address this issue, we impose a convolutional architecture on the neural BP decoder, enabling weight sharing across the spatially homogeneous structure of the code's factor graph. This design allows a model trained on a modest-size topological code to be directly transferred to much larger instances, preserving decoding quality while dramatically lowering the training burden. Our numerical experiments on toric-code lattices of various sizes demonstrate that this technique does not result in a noticeable loss in performance.
Abstract:Quantum error correction (QEC) is critical for scalable fault-tolerant quantum computing. Topological codes, such as the toric code, offer hardware-efficient architectures but their Tanner graphs contain many girth-4 cycles that degrade the performance of belief-propagation (BP) decoding. For this reason, BP decoding is typically followed by a more complex second stage decoder such as minimum-weight perfect matching. These combined decoders achieve a remarkable performance, albeit at the cost of increased complexity. In this paper we propose two key improvements for the decoding of toric code. The first one is replacing the BP decoder by a neural BP decoder, giving rise to the neural belief-matching decoder which substantially decreases the average decoding complexity. The main drawback of this approach is the high cost associated with the training of the neural BP decoder. To address this issue, we impose a convolutional architecture on the neural BP decoder, enabling weight sharing across the spatially homogeneous structure of the code's factor graph. This design allows a model trained on a modest-size topological code to be directly transferred to much larger instances, preserving decoding quality while dramatically lowering the training burden. Our numerical experiments on toric-code lattices of various sizes demonstrate that this technique does not result in a noticeable loss in performance.
arXiv:2603.21730 [quant-ph]
(or arXiv:2603.21730v2 [quant-ph] for this version)
https://doi.org/10.48550/arXiv.2603.21730 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 297 words
Related coverage
Streaming Belief Propagation on Mixed-Alphabet Tanner Graphs for Practical Quantum Memory
Quantum Journal · Sep 10, 2026
Qubit-centric Transformer for Surface Code Decoding
arXiv · Oct 7, 2026
News
Quantum Computing Report · Jul 25, 2026
Yan and Colleagues Develop Neural Transfer Unification for Efficient Quantum Decoding
Quantum Zeitgeist · Jul 23, 2026