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

TL;DR

This paper introduces QuantumSMoE, a novel quantum vision transformer decoder that leverages code structure and a mixture of experts to improve surface code decoding efficiency and accuracy.

Contribution

It presents QuantumSMoE, a new decoder combining vision transformer architecture with code-specific embeddings and adaptive masking for better quantum error correction.

Findings

QuantumSMoE outperforms existing ML decoders on the toric code.

QuantumSMoE surpasses classical decoding baselines in accuracy.

The mixture of experts layer enhances scalability and performance.

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.