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.
@article{arxiv.2410.22735,
title = {MIXAD: Memory-Induced Explainable Time Series Anomaly Detection},
author = {Minha Kim and Kishor Kumar Bhaumik and Amin Ahsan Ali and Simon S. Woo},
journal= {arXiv preprint arXiv:2410.22735},
year = {2024}
}