MgEL: Quantum Entanglement-Inspired Evidence Fusion for Learning with Noisy Labels

With the rise of data engineering-driven automatic annotation strategies, deep learning has demonstrated remarkable performance and strong competitiveness in intelligent fault diagnosis. However, the inherent limitations of automatic annotators inevitably introduce noisy labels, which in turn hinder the generalization and accuracy of diagnostic models. Although numerous Learning with Noisy Labels (LNL) methods attempt to alleviate the impact of label noise through sample selection or label correction, most rely heavily on model predictions to guide training. This self-reinforcing mechanism frequently leads to confirmation bias, especially under high-noise conditions, thereby limiting their effectiveness. To address these challenges while preserving the full data utility, this paper proposes a novel approach termed the Multi-granularity Evidence Labels (MgEL), inspired by the principles of quantum entanglement and collapse. In MgEL, we perform feature-space fusion between entangled sub-distributions to construct a superposition state, from which two auxiliary labels are derived: a pseudo-label obtained by selecting the class with the maximum amplitude and a collapsed label sampled probabilistically according to the class-wise amplitude distribution. The collapsed label represents an uncertainty-aware observation, while the pseudo-label represents the most confident class estimation. These are then fused with the original annotation to form multi-granularity evidence labels. This approach allows MgEL to suppress confirmation bias and improve robustness under noisy supervision. Extensive experiments validate the effectiveness and reliability of MgEL, particularly in high-noise scenarios (e.g., noise intensity $\eta \ge 80\%$), underscoring its potential for practical deployment in low-cost, data-driven intelligent fault diagnosis systems.