A Mixture of Experts Vision Transformer for High-Fidelity Surface Code Decoding

• URL: http://arxiv.org/abs/2601.12483v1
• Date: Sun, 18 Jan 2026 16:49:59 GMT
• Title: A Mixture of Experts Vision Transformer for High-Fidelity Surface Code Decoding
• Authors: Hoang Viet Nguyen, Manh Hung Nguyen, Hoang Ta, Van Khu Vu, Yeow Meng Chee,
• Abstract summary: Topological stabilizer codes are particularly appealing due to their geometric locality and practical relevance.<n>We propose QuantumSMoE, a quantum vision transformer based decoder that incorporates code structure through plus shaped embeddings.<n> Experiments on the toric code demonstrate that QuantumSMoE outperforms state-of-the-art machine learning decoders.
• Score: 12.998419492098462
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Quantum error correction is a key ingredient for large scale quantum computation, protecting logical information from physical noise by encoding it into many physical qubits. Topological stabilizer codes are particularly appealing due to their geometric locality and practical relevance. In these codes, stabilizer measurements yield a syndrome that must be decoded into a recovery operation, making decoding a central bottleneck for scalable real time operation. Existing decoders are commonly classified into two categories. Classical algorithmic decoders provide strong and well established baselines, but may incur substantial computational overhead at large code distances or under stringent latency constraints. Machine learning based decoders offer fast GPU inference and flexible function approximation, yet many approaches do not explicitly exploit the lattice geometry and local structure of topological codes, which can limit performance. In this work, we propose QuantumSMoE, a quantum vision transformer based decoder that incorporates code structure through plus shaped embeddings and adaptive masking to capture local interactions and lattice connectivity, and improves scalability via a mixture of experts layer with a novel auxiliary loss. Experiments on the toric code demonstrate that QuantumSMoE outperforms state-of-the-art machine learning decoders as well as widely used classical baselines.

Related papers

• Neural Decoders for Universal Quantum Algorithms [0.43553942673960666]
  We introduce a modular attention-based neural decoder that learns gate-induced correlations.<n>Our decoders achieve fast inference and logical error rates comparable to most-likely-error decoders.<n>These results establish neural decoders as practical, versatile, and high-performance tools for quantum computing.
  arXiv  Detail & Related papers  (2025-09-14T17:51:46Z)
• A Unitary Encoder for Surface Codes [0.0]
  We propose a new non-local unitary circuit to encode a surface code state based on a code conversion between rotated and regular surface codes.<n>Our encoder provides practical advantage in platforms where non-local interactions are available such as neutral atoms and trapped ions.
  arXiv  Detail & Related papers  (2025-06-04T15:45:03Z)
• Bubble Clustering Decoder for Quantum Topological Codes [8.62986288837424]
  We introduce the bubble clustering decoder for quantum surface codes, which serves as a low-latency replacement for MWPM.<n>This speed boost is obtained leveraging an efficient cluster generation based on bubbles centered on defects.<n>For moderate physical error rates, this is equivalent to linear complexity in the number of data qubits.
  arXiv  Detail & Related papers  (2025-04-02T12:02:34Z)
• Accelerating Error Correction Code Transformers [56.75773430667148]
  We introduce a novel acceleration method for transformer-based decoders. We achieve a 90% compression ratio and reduce arithmetic operation energy consumption by at least 224 times on modern hardware.
  arXiv  Detail & Related papers  (2024-10-08T11:07:55Z)
• Localized statistics decoding for quantum low-density parity-check codes [3.716393259548592]
  We introduce localized statistics decoding for arbitrary quantum low-density parity-check codes.<n>Our decoder is more amenable to implementation on specialized hardware, positioning it as a promising candidate for decoding real-time syndromes from experiments.
  arXiv  Detail & Related papers  (2024-06-26T18:00:09Z)
• Learning Linear Block Error Correction Codes [62.25533750469467]
  We propose for the first time a unified encoder-decoder training of binary linear block codes. We also propose a novel Transformer model in which the self-attention masking is performed in a differentiable fashion for the efficient backpropagation of the code gradient.
  arXiv  Detail & Related papers  (2024-05-07T06:47:12Z)
• Small Quantum Codes from Algebraic Extensions of Generalized Bicycle Codes [4.299840769087443]
  Quantum LDPC codes range from the surface code, which has a vanishing encoding rate, to very promising codes with constant encoding rate and linear distance. We devise small quantum codes that are inspired by a subset of quantum LDPC codes, known as generalized bicycle (GB) codes.
  arXiv  Detail & Related papers  (2024-01-15T10:38:13Z)
• The END: An Equivariant Neural Decoder for Quantum Error Correction [73.4384623973809]
  We introduce a data efficient neural decoder that exploits the symmetries of the problem. We propose a novel equivariant architecture that achieves state of the art accuracy compared to previous neural decoders.
  arXiv  Detail & Related papers  (2023-04-14T19:46:39Z)
• Deep Quantum Error Correction [73.54643419792453]
  Quantum error correction codes (QECC) are a key component for realizing the potential of quantum computing. In this work, we efficiently train novel emphend-to-end deep quantum error decoders. The proposed method demonstrates the power of neural decoders for QECC by achieving state-of-the-art accuracy.
  arXiv  Detail & Related papers  (2023-01-27T08:16:26Z)
• Adversarial Neural Networks for Error Correcting Codes [76.70040964453638]
  We introduce a general framework to boost the performance and applicability of machine learning (ML) models. We propose to combine ML decoders with a competing discriminator network that tries to distinguish between codewords and noisy words. Our framework is game-theoretic, motivated by generative adversarial networks (GANs)
  arXiv  Detail & Related papers  (2021-12-21T19:14:44Z)
• Dense Coding with Locality Restriction for Decoder: Quantum Encoders vs. Super-Quantum Encoders [67.12391801199688]
  We investigate dense coding by imposing various locality restrictions to our decoder. In this task, the sender Alice and the receiver Bob share an entangled state.
  arXiv  Detail & Related papers  (2021-09-26T07:29:54Z)

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.