模块特定的Lipschitz调制用于容错多模态表示学习
Layer-Specific Lipschitz Modulation for Fault-Tolerant Multimodal Representation Learning
AI总结：
本文提出了一种结合自监督异常检测与误差校正的框架，通过模块特定的Lipschitz调制和梯度裁剪提升多模态表示学习的容错能力。
摘要：
现代部署于工业和安全关键环境的多模态系统必须在部分传感器故障、信号退化或跨模态不一致时保持可靠。本文介绍了一个数学基础的框架，用于容错的多模态表示学习，该框架在单一架构中统一了自监督异常检测和误差校正。基于对扰动传播的理论分析，我们推导出基于Lipschitz和雅可比的准则，以确定神经算子是否放大或衰减局部故障。受此理论指导，我们提出一个两阶段自监督训练方案：先在干净数据上预训练多模态卷积自编码器以在潜在空间中保留局部异常信号，然后扩展为由密集层组成的可学习计算块，用于校正和对比学习目标以识别异常。此外，我们引入模块特定的Lipschitz调制和梯度裁剪作为控制灵敏度的原理性机制。在多模态故障数据集上的实验结果表明，所提出的方法在传感器损坏下的异常检测准确性和重建性能均有提升。总体而言，该框架弥合了分析鲁棒性保证与实用容错多模态学习之间的差距。
英文摘要：
Modern multimodal systems deployed in industrial and safety-critical environments must remain reliable under partial sensor failures, signal degradation, or cross-modal inconsistencies. This work introduces a mathematically grounded framework for fault-tolerant multimodal representation learning that unifies self-supervised anomaly detection and error correction within a single architecture. Building upon a theoretical analysis of perturbation propagation, we derive Lipschitz- and Jacobian-based criteria that determine whether a neural operator amplifies or attenuates localized faults. Guided by this theory, we propose a two-stage self-supervised training scheme: pre-training a multimodal convolutional autoencoder on clean data to preserve localized anomaly signals in the latent space, and expanding it with a learnable compute block composed of dense layers for correction and contrastive objectives for anomaly identification. Furthermore, we introduce layer-specific Lipschitz modulation and gradient clipping as principled mechanisms to control sensitivity across detection and correction modules. Experimental results on multimodal fault datasets demonstrate that the proposed approach improves both anomaly detection accuracy and reconstruction under sensor corruption. Overall, this framework bridges the gap between analytical robustness guarantees and practical fault-tolerant multimodal learning.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
