FT-MoE：面向容错计算的可持续学习专家混合模型
FT-MoE: Sustainable-learning Mixture of Experts for Fault-Tolerant Computing
AI总结：
FT-MoE通过双路径架构和两阶段学习方案，实现高精度故障检测和分类，提升容错计算的可持续学习能力。
摘要：
智能容错（FT）计算最近在主动预测和诊断故障方面展现了显著优势，从而确保可靠的服务交付。然而，由于故障知识的异质性、动态负载和有限的数据支持，现有的基于深度学习的FT算法在故障检测质量和训练效率方面面临挑战。这主要是因为它们对故障知识感知的同质化难以完全捕捉多样且复杂的故障模式。为了解决这些挑战，我们提出了FT-MoE，一种基于双路径架构的可持续学习容错计算框架，用于高精度的故障检测和分类。该模型采用专家混合（MoE）架构，使不同参数学习不同的故障知识。此外，我们采用两阶段学习方案，结合全面的离线训练与持续的在线调优，使模型能够根据不断变化的实时负载自适应优化其参数。为了便于实际评估，我们构建了一个新的故障检测和分类数据集用于边缘网络，包含10,000个区间，具有精细的资源特征，超过了现有数据集在规模和粒度上的表现。最后，我们在FT基准上进行了广泛的实验以验证FT-MoE的有效性。结果表明，我们的模型优于最先进的方法。
英文摘要：
Intelligent fault-tolerant (FT) computing has recently demonstrated significant advantages in predicting and diagnosing faults proactively, thereby ensuring reliable service delivery. However, due to the heterogeneity of fault knowledge, dynamic workloads, and limited data support, existing deep learning-based FT algorithms face challenges in fault detection quality and training efficiency. This is primarily because their homogenization of fault knowledge perception difficuties to fully capture diverse and complex fault patterns. To address these challenges, we propose FT-MoE, a sustainable-learning fault-tolerant computing framework based on a dual-path architecture for high-accuracy fault detection and classification. This model employs a mixture-of-experts (MoE) architecture, enabling different parameters to learn distinct fault knowledge. Additionally, we adopt a two-stage learning scheme that combines comprehensive offline training with continual online tuning, allowing the model to adaptively optimize its parameters in response to evolving real-time workloads. To facilitate realistic evaluation, we construct a new fault detection and classification dataset for edge networks, comprising 10,000 intervals with fine-grained resource features, surpassing existing datasets in both scale and granularity. Finally, we conduct extensive experiments on the FT benchmark to verify the effectiveness of FT-MoE. Results demonstrate that our model outperforms state-of-the-art methods.
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。
