cs.LGNov 11, 2026

When Does Causality Help in Multivariate Time-Series Anomaly Detection?

Authors: Long Zhang, Wei Huang, Aishui Rao, Jian Hu, Binxiang Wu, Jie Li, Chen Gong, Linxi Feng

Organizations: China Satellite Maritime Tracking and Control Department, Jiangyin, China, 214400

Abstract

Causality-aware scoring is common in multivariate time-series anomaly detection, yet the literature rarely states when it helps. Holding one causality-guided autoencoder (DeCauAE) fixed, we vary graph quality, anomaly type and protocol against ground truth. Graph quality fixes the payoff: on a twenty-variable DAG the gain over a graph-free autoencoder decays as the graph is corrupted. Anomaly type fixes the target: the structural factor lifts window F1 from 0.800 to 0.976 where anomalies break conditional structure, and its advantage vanishes below a break severity s 0.3. Protocol fixes the ranking: point-adjusted F1 lets a random score match the full model, while range-aware VUS separates the autoencoder family from the classical baselines. On real benchmarks the causal module pays only where density makes a system eligible and cross-subsample reproducibility selects entities inside it; enabling it everywhere costs 0.012 VUS-ROC. The structural factor also transfers to classical detectors .

Explore similar work

CardsList
  1. Structured Temporal Causality for Interpretable Multivariate Time Series Anomaly Detection

    Oct 18, 2025Dongchan Cho, Jiho Han, Keumyeong Kang +3Time-Series Anomaly DetectionUnsupervised Anomaly Detection

  2. Correlation-Aware Reconstruction for Multivariate Time Series Anomaly Detection

    Oct 11, 2026Md. Johir Raihan, Zahra Zamanzadeh Darban, Yueyang Liu +3Time-Series Anomaly DetectionAnomaly Detection