MIXAD：记忆诱导的可解释时间序列异常检测
MIXAD: Memory-Induced Explainable Time Series Anomaly Detection
AI总结：
针对现有时间序列异常检测方法重性能轻可解释性的问题，提出结合记忆网络与时空单元的MIXAD模型及新型异常评分法，在保证检测性能的同时，可解释性指标较最优基线提升超34%。
摘要：
对于现代工业应用而言，准确检测并诊断多变量时间序列数据中的异常至关重要。尽管存在此类需求，大多数当前最优方法往往更侧重检测性能而非模型可解释性。为填补这一空白，我们提出MIXAD（记忆诱导的可解释时间序列异常检测），这是一款专为可解释异常检测设计的模型。MIXAD结合记忆网络与时空处理单元，以理解传感器关系中固有的复杂动态和拓扑结构。我们还提出了一种新颖的异常评分方法，可检测异常发生时记忆激活模式的显著变化。我们的方法不仅保证了良好的检测性能，在可解释性指标上还优于当前最优基线34.30%和34.51%。
英文摘要：
For modern industrial applications, accurately detecting and diagnosing anomalies in multivariate time series data is essential. Despite such need, most state-of-the-art methods often prioritize detection performance over model interpretability. Addressing this gap, we introduce MIXAD (Memory-Induced Explainable Time Series Anomaly Detection), a model designed for interpretable anomaly detection. MIXAD leverages a memory network alongside spatiotemporal processing units to understand the intricate dynamics and topological structures inherent in sensor relationships. We also introduce a novel anomaly scoring method that detects significant shifts in memory activation patterns during anomalies. Our approach not only ensures decent detection performance but also outperforms state-of-the-art baselines by 34.30% and 34.51% in interpretability metrics.
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。
