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

2026-01-18

AI Summary

This work addresses the performance bottlenecks of conventional decoders in large-scale surface code quantum error correction under high-distance and low-latency regimes. The authors propose QuantumSMoE, the first framework integrating a structure-aware Vision Transformer with a Mixture-of-Experts (MoE) mechanism. By introducing cross-shaped embeddings and adaptive mask modeling, the method effectively captures local lattice topology, while a novel auxiliary loss function enhances the exploitation of spatial locality. Evaluated on the toric code, QuantumSMoE significantly outperforms both existing machine learning–based and classical decoders, achieving superior scalability and GPU-accelerated inference efficiency without compromising decoding fidelity.

Technology Category

• Machine Learning: Quantum Machine Learning
• Search and Optimization: Learning to Search
• Computer Vision: Large Vision Models

Application Category

• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

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.

Problem

• quantum error correction
• surface code decoding
• topological stabilizer codes
• syndrome decoding
• scalable decoding

Innovation

• Mixture of Experts
• Vision Transformer
• Quantum Error Correction
• Topological Codes
• Plus-shaped Embedding