Cluster-Aware Causal Mixer for Online Anomaly Detection in Multivariate Time Series
Not on the map. Why?
Abstract (arXiv)
Early and accurate detection of anomalies in time-series data is critical due to the substantial risks associated with false or missed detections. While MLP-based mixer models have shown promise in time-series analysis, they do not maintain temporal causality during data processing. Moreover, real-world multivariate time series often contain numerous channels with diverse inter-channel correlations. Spurious correlations in the reconstructed time series lead to noisy representations, resulting in inaccurate anomaly detection. In addition, anomaly scoring methods that ignore temporal continuity can mislead sequential detection. To address these challenges, we propose a cluster-aware causal mixer for multivariate time-series anomaly detection. Channels are grouped into clusters based on their correlations, and each cluster is embedded through a dedicated embedding layer. A causal mixer is introduced to integrate information while maintaining temporal causality. We further develop a sequential anomaly-scoring method that accumulates evidence over time and refines anomaly boundaries. Our proposed model operates in an online fashion, making it suitable for real-time time-series anomaly detection. Experimental evaluations across six public benchmark datasets demonstrate that the proposed approach consistently achieves superior performance.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 30 of its 55 references that are in the map. First posted on arXiv 30 May 2025.
Builds on
30 of 55 references.
References · 30
- 2022Are Transformers Effective for Time Series Forecasting?cited by 1,424
- 2022TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysiscited by 1,058
- 2018Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholdingcited by 410
- 2021Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancycited by 394
- 2024TimeMixer: Decomposable Multiscale Mixing for Time Series Forecastingcited by 346
- 2021Graph Neural Network-Based Anomaly Detection in Multivariate Time Seriescited by 301
- 2023TSMixer: An All-MLP Architecture for Time Series Forecastingcited by 240
- 2022TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Datacited by 214
- 2017A Multimodal Anomaly Detector for Robot-Assisted Feeding Using an LSTM-based Variational Autoencodercited by 209
- 2020A review on outlier/anomaly detection in time series datacited by 189
- 2018A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Datacited by 182
- 2019MAD-GAN: Multivariate Anomaly Detection for Time Series Data with Generative Adversarial Networkscited by 176
18 more
- 2020Multivariate Time-series Anomaly Detection via Graph Attention Networkcited by 167
- 2024Tiny Time Mixers (TTMs): Fast Pre-trained Models for Enhanced Zero/Few-Shot Forecasting of Multivariate Time Seriescited by 127
- 2021Learning Graph Structures with Transformer for Multivariate Time Series Anomaly Detection in IoTcited by 104
- 2015Learning to Diagnose with LSTM Recurrent Neural Networkscited by 99
- 2021Towards a Rigorous Evaluation of Time-series Anomaly Detectioncited by 97
- 2024CATCH: Channel-Aware multivariate Time Series Anomaly Detection via Frequency Patchingcited by 94
- 2021An Evaluation of Anomaly Detection and Diagnosis in Multivariate Time Seriescited by 68
- 2023MEMTO: Memory-guided Transformer for Multivariate Time Series Anomaly Detectioncited by 26
- 2024WPMixer: Efficient Multi-Resolution Mixing for Long-Term Time Series Forecastingcited by 26
- 2024Graph Mixture of Experts and Memory-augmented Routers for Multivariate Time Series Anomaly Detectioncited by 20
- 2023Nominality Score Conditioned Time Series Anomaly Detection by Point/Sequential Reconstructioncited by 17
- 2024Position: Quo Vadis, Unsupervised Time Series Anomaly Detection?cited by 17
- 2022TiSAT: Time Series Anomaly Transformercited by 15
- 2024PatchAD: A Lightweight Patch-based MLP-Mixer for Time Series Anomaly Detectioncited by 12
- 2024Sub-Adjacent Transformer: Improving Time Series Anomaly Detection with Reconstruction Error from Sub-Adjacent Neighborhoodscited by 10
- 2016Supervised Anomaly Detection in Uncertain Pseudoperiodic Data Streamscited by 4
- 2025Noise-Resilient Point-wise Anomaly Detection in Time Series Using Weak Segment Labelscited by 3
- 2025TSKANMixer: Kolmogorov-Arnold Networks with MLP-Mixer Model for Time Series Forecastingcited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.