mlsanityData to 7 Oct 2026

Revisiting VAE for Unsupervised Time Series Anomaly Detection: A Frequency Perspective

arXiv 2402.02820 ↗First posted 5 Feb 2024cs.LGcited by 22

Not on the map. Why?

Abstract (arXiv)

Time series Anomaly Detection (AD) plays a crucial role for web systems. Various web systems rely on time series data to monitor and identify anomalies in real time, as well as to initiate diagnosis and remediation procedures. Variational Autoencoders (VAEs) have gained popularity in recent decades due to their superior de-noising capabilities, which are useful for anomaly detection. However, our study reveals that VAE-based methods face challenges in capturing long-periodic heterogeneous patterns and detailed short-periodic trends simultaneously. To address these challenges, we propose Frequency-enhanced Conditional Variational Autoencoder (FCVAE), a novel unsupervised AD method for univariate time series. To ensure an accurate AD, FCVAE exploits an innovative approach to concurrently integrate both the global and local frequency features into the condition of Conditional Variational Autoencoder (CVAE) to significantly increase the accuracy of reconstructing the normal data. Together with a carefully designed "target attention" mechanism, our approach allows the model to pick the most useful information from the frequency domain for better short-periodic trend construction. Our FCVAE has been evaluated on public datasets and a large-scale cloud system, and the results demonstrate that it outperforms state-of-the-art methods. This confirms the practical applicability of our approach in addressing the limitations of current VAE-based anomaly detection models.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Builds on 18 of its 63 references that are in the map. First posted on arXiv 5 Feb 2024.

Builds on

18 of 63 references.

References · 18

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,141
  3. 2018Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholdingcited by 407
  4. 2021Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancycited by 387
  5. 2020Time Series Data Augmentation for Deep Learning: A Surveycited by 225
  6. 2018Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applicationscited by 223
  7. 2019Time-Series Anomaly Detection Service at Microsoftcited by 163
  8. 2015Evaluating Real-time Anomaly Detection Algorithms - the Numenta Anomaly Benchmarkcited by 87
  9. 2023Automatic Root Cause Analysis via Large Language Models for Cloud Incidentscited by 82
  10. 2020Time Series Change Point Detection with Self-Supervised Contrastive Predictive Codingcited by 58
  11. 2022TFAD: A Decomposition Time Series Anomaly Detection Architecture with Time-Frequency Analysiscited by 48
  12. 2021End-to-End User Behavior Retrieval in Click-Through RatePrediction Modelcited by 45
6 more
  1. 2021Neural Contextual Anomaly Detection for Time Seriescited by 42
  2. 2022Constructing Large-Scale Real-World Benchmark Datasets for AIOpscited by 19
  3. 2021CAMul: Calibrated and Accurate Multi-view Time-Series Forecastingcited by 17
  4. 2023Robust Multimodal Failure Detection for Microservice Systemscited by 13
  5. 2023TraceDiag: Adaptive, Interpretable, and Efficient Root Cause Analysis on Large-Scale Microservice Systemscited by 7
  6. 2023Beyond Sharing: Conflict-Aware Multivariate Time Series Anomaly Detectioncited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 8; 2026: 10.

22 papers.

Sort:

By area:

  1. 2024Deep Time Series Models: A Comprehensive Survey and Benchmarkcited by 191
  2. 2025Flow-of-Action: SOP Enhanced LLM-Based Multi-Agent System for Root Cause Analysiscited by 32
  3. 2024TimeSeriesBench: An Industrial-Grade Benchmark for Time Series Anomaly Detection Modelscited by 22
  4. 2024KAN-AD: Time Series Anomaly Detection with Kolmogorov-Arnold Networkscited by 20
  5. 2025K2VAE: A Koopman-Kalman Enhanced Variational AutoEncoder for Probabilistic Time Series Forecastingcited by 7
  6. 2026UModel: An Agent-Ready Observability Data Modeling Method at Scalecited by 1
  7. 2026LLM Agents for Time-Series: A Surveycited by 1
  8. 2024Learning Latent Spaces for Domain Generalization in Time Series Forecastingcited by 0
  9. 2025BEAT: Balanced Frequency Adaptive Tuning for Long-Term Time-Series Forecastingcited by 0
  10. 2025A Split-Window Transformer for Multi-Model Sequence Spammer Detection using Multi-Model Variational Autoencodercited by 0
  11. 2025Energy-Aware Pattern Disentanglement: A Generalizable Pattern Assisted Architecture for Multi-task Time Series Analysiscited by 0
  12. 2025Wavelet Scattering Transform and Fourier Representation for Offline Detection of Malicious Clients in Federated Learningcited by 0
10 more
  1. 2025ViTs: Teaching Machines to See Time Series Anomalies Like Human Expertscited by 0
  2. 2025LPCVAE: A Conditional VAE with Long-Term Dependency and Probabilistic Time-Frequency Fusion for Time Series Anomaly Detectioncited by 0
  3. 2026Strong Linear Baselines Strike Back: Closed-Form Linear Models as Gaussian Process Conditional Density Estimators for TSADcited by 0
  4. 2026LEFT: Learnable Fusion of Tri-view Tokens for Unsupervised Time Series Anomaly Detectioncited by 0
  5. 2026Contextual and Seasonal LSTMs for Time Series Anomaly Detectioncited by 0
  6. 2026Bridging Classification and Reconstruction: Cooperative Time Series Anomaly Detectioncited by 0
  7. 2026CAAD: Causality-Aware Multivariate Time Series Anomaly Detection via Multi-Scale Alignment and Structural Causal Consistencycited by 0
  8. 2026Lightweight Multi-Scale Anomaly Detection for Resource-Constrained Edge Devicescited by 0
  9. 2026Structured Frequency-Domain Evidence for LLM-Based Time-Series Anomaly Detectioncited by 0
  10. 2026DrafTS: Time-Aware Decomposition with Residual Correction for Time Series Modelingcited by 0