MIXAD: Memory-Induced Explainable Time Series Anomaly Detection

TL;DR

MIXAD is a novel model for time series anomaly detection that combines memory networks and spatiotemporal analysis to improve interpretability without sacrificing detection accuracy.

Contribution

It introduces a memory-induced approach with a new scoring method, enhancing interpretability and performance in multivariate time series anomaly detection.

Findings

Outperforms baselines by over 34% in interpretability metrics.

Achieves comparable detection performance to state-of-the-art methods.

Effectively captures complex sensor relationships and dynamics.

Abstract

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.