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

• URL: http://arxiv.org/abs/2607.08555v1
• Date: Thu, 09 Jul 2026 14:46:10 GMT
• Title: CAAD: Causality-Aware Multivariate Time Series Anomaly Detection via Multi-Scale Alignment and Structural Causal Consistency
• Abstract summary: We propose a novel framework that reframes anomaly detection as the continuous verification of Granger causality.<n>The proposed framework leverages multi-scale alignment to internalize system dynamics.<n>Experiments on real-world industrial datasets demonstrate that the CAAD achieves high-precision anomaly detection.
• Score: 9.032903163326027
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Robust Fault Detection in Mechanical Multimodal Time Series via Self-Supervised Cross-Modal Reconstruction [13.337672748422444]
  We propose a multimodal anomaly detection framework based on cross-modal reconstruction of heterogeneous time-series sensor data.<n>Rather than modeling each modality independently, the framework learns system dynamics by reconstructing each modality from the others.<n>This integrates information across sensing channels without requiring explicit temporal alignment or identical sampling rates.
  arXiv  Detail & Related papers  (2026-09-14T20:24:53Z)
• Causal Discovery with Inverted Self-attention for Multivariate Time Series [21.018583540683917]
  We propose a novel framework that leverages self-attention mechanisms within the transformer architecture for causal discovery.<n>Our approach emphasizes latent and indirect causal relationships by inverting tokens and inducing sparsity in attention scores.<n>We also develop a global causal algorithm to identify global causal links, providing a holistic metric for causal influence.
  arXiv  Detail & Related papers  (2026-07-30T13:49:46Z)
• Towards Anomaly Detection on Relational Data [51.473064583839296]
  We propose a reconstruction-based framework that captures anomalies from both attribute and relational edge reconstruction.<n>RelAD consistently outperforms other baselines while achieving competitive efficiency.
  arXiv  Detail & Related papers  (2026-06-17T02:36:32Z)
• Causally-Constrained Probabilistic Forecasting for Time-Series Anomaly Detection [1.8995711908407733]
  This study introduces a causally-constrained probabilistic forecasting framework for anomaly detection.<n>It integrates an explicit time-lagged causal graph prior with deep sequence modeling.<n>Experiments indicate that the proposed method achieves state-of-the-art detection performance.
  arXiv  Detail & Related papers  (2026-04-20T09:24:28Z)
• Out of Context: Reliability in Multimodal Anomaly Detection Requires Contextual Inference [54.774686416991386]
  We argue that multimodal anomaly detection should be reframed as a cross-modal contextual inference problem.<n>This perspective has implications for model design, evaluation protocols, and benchmark construction.
  arXiv  Detail & Related papers  (2026-04-14T19:32:55Z)
• Unifying Explainable Anomaly Detection and Root Cause Analysis in Dynamical Systems [24.640375297580288]
  This paper addresses the challenges of anomaly detection, root cause localization, and anomaly type classification in dynamical systems governed by ordinary differential equations (ODEs)<n>We propose the Interpretable Causality Ordinary Differential Equation (ICODE) Networks, a model-intrinsic explainable learning framework.<n>ICODE is designed to simultaneously perform anomaly detection, root cause analysis (RCA), and anomaly type classification within a single, interpretable framework.
  arXiv  Detail & Related papers  (2025-02-17T18:01:07Z)
• Causal Temporal Regime Structure Learning [49.77103348208835]
  We present CASTOR, a novel method that concurrently learns the Directed Acyclic Graph (DAG) for each regime.<n>We establish the identifiability of the regimes and DAGs within our framework.<n>Experiments show that CASTOR consistently outperforms existing causal discovery models.
  arXiv  Detail & Related papers  (2023-11-02T17:26:49Z)
• Causal Disentanglement Hidden Markov Model for Fault Diagnosis [55.90917958154425]
  We propose a Causal Disentanglement Hidden Markov model (CDHM) to learn the causality in the bearing fault mechanism. Specifically, we make full use of the time-series data and progressively disentangle the vibration signal into fault-relevant and fault-irrelevant factors. To expand the scope of the application, we adopt unsupervised domain adaptation to transfer the learned disentangled representations to other working environments.
  arXiv  Detail & Related papers  (2023-08-06T05:58:45Z)
• DyEdgeGAT: Dynamic Edge via Graph Attention for Early Fault Detection in IIoT Systems [12.641578474466646]
  DyEdgeGAT is a novel approach for early-stage fault detection in IIoT systems. It incorporates operating condition contexts into node dynamics modeling, enhancing its accuracy and robustness. We rigorously evaluated DyEdgeGAT using both a synthetic dataset and a real-world industrial-scale flow facility benchmark.
  arXiv  Detail & Related papers  (2023-07-07T12:22:16Z)
• Causality-Based Multivariate Time Series Anomaly Detection [63.799474860969156]
  We formulate the anomaly detection problem from a causal perspective and view anomalies as instances that do not follow the regular causal mechanism to generate the multivariate data. We then propose a causality-based anomaly detection approach, which first learns the causal structure from data and then infers whether an instance is an anomaly relative to the local causal mechanism. We evaluate our approach with both simulated and public datasets as well as a case study on real-world AIOps applications.
  arXiv  Detail & Related papers  (2022-06-30T06:00:13Z)
• Consistency of mechanistic causal discovery in continuous-time using Neural ODEs [85.7910042199734]
  We consider causal discovery in continuous-time for the study of dynamical systems. We propose a causal discovery algorithm based on penalized Neural ODEs.
  arXiv  Detail & Related papers  (2021-05-06T08:48:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.