CAAD: Causality-Aware Multivariate Time Series Anomaly Detection via Multi-Scale Alignment and Structural Causal Consistency

2026-07-09

AI Summary

This work proposes a novel paradigm for anomaly detection that shifts focus from superficial temporal similarity to the disruption of intrinsic causal structures within systems. By reframing anomaly detection as the continuous validation of Granger causality consistency through exogenous variables, the method captures subtle causal fractures often missed by conventional approaches. It introduces multi-scale alignment to model dynamic system evolution and employs a gradient-based causal matrix to quantify deviations in causal topology. Centered on causal consistency as the core diagnostic criterion, the approach achieves state-of-the-art performance across multiple real-world industrial datasets, offering both high detection accuracy and enhanced interpretability.

Abstract

The operational integrity of complex industrial systems relies on precise anomaly detection and diagnosis. The vast majority of existing methods narrowly focus on capturing temporal similarities of representations, often overlooking the disruption of internal causal relationships, which characterizes system failures and latent anomalies. In this paper, we propose a novel framework (CAAD) that reframes anomaly detection as the continuous verification of Granger causality consistency through exogenous variables. Specifically, the CAAD framework models exogenous time-series variables as residuals, identifying anomalies as significant deviations caused by external interventions. The proposed framework leverages multi-scale alignment to internalize system dynamics and utilizes a gradient-based matrix to monitor internal causal relationship breakdowns. By quantifying causal deviations of both dynamic evolution and relational topology, the CAAD is able to capture subtle causal shifts to achieve precise anomaly detection. Extensive experiments on real-world industrial datasets demonstrate that the CAAD achieves high-precision anomaly detection, outperforming most state-of-the-art baselines.

Problem

• anomaly detection
• causal relationships
• multivariate time series
• Granger causality
• industrial systems

Innovation

• Causality-Aware
• Granger Causality Consistency
• Multi-Scale Alignment
• Structural Causal Model
• Exogenous Residual Modeling