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

arXiv: https://arxiv.org/abs/2402.02820 · HTML: https://mlsanity.com/paper/2402.02820/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 63 references that are in the map.
- First posted on arXiv 5 Feb 2024.

## Builds on (most cited first, 18 of 18)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting](https://mlsanity.com/paper/2012.07436/) (2020)
- [Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholding](https://mlsanity.com/paper/1802.04431/) (2018)
- [Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy](https://mlsanity.com/paper/2110.02642/) (2021)
- [Time Series Data Augmentation for Deep Learning: A Survey](https://mlsanity.com/paper/2002.12478/) (2020)
- [Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applications](https://mlsanity.com/paper/1802.03903/) (2018)
- [Time-Series Anomaly Detection Service at Microsoft](https://mlsanity.com/paper/1906.03821/) (2019)
- [Evaluating Real-time Anomaly Detection Algorithms - the Numenta Anomaly Benchmark](https://mlsanity.com/paper/1510.03336/) (2015)
- [Automatic Root Cause Analysis via Large Language Models for Cloud Incidents](https://mlsanity.com/paper/2305.15778/) (2023)
- [Time Series Change Point Detection with Self-Supervised Contrastive Predictive Coding](https://mlsanity.com/paper/2011.14097/) (2020)
- [TFAD: A Decomposition Time Series Anomaly Detection Architecture with Time-Frequency Analysis](https://mlsanity.com/paper/2210.09693/) (2022)
- [End-to-End User Behavior Retrieval in Click-Through RatePrediction Model](https://mlsanity.com/paper/2108.04468/) (2021)
- [Neural Contextual Anomaly Detection for Time Series](https://mlsanity.com/paper/2107.07702/) (2021)
- [Constructing Large-Scale Real-World Benchmark Datasets for AIOps](https://mlsanity.com/paper/2208.03938/) (2022)
- [CAMul: Calibrated and Accurate Multi-view Time-Series Forecasting](https://mlsanity.com/paper/2109.07438/) (2021)
- [Robust Multimodal Failure Detection for Microservice Systems](https://mlsanity.com/paper/2305.18985/) (2023)
- [TraceDiag: Adaptive, Interpretable, and Efficient Root Cause Analysis on Large-Scale Microservice Systems](https://mlsanity.com/paper/2310.18740/) (2023)
- [Beyond Sharing: Conflict-Aware Multivariate Time Series Anomaly Detection](https://mlsanity.com/paper/2308.08915/) (2023)

## Built on by (most cited first, 24 of 24)

- [Deep Time Series Models: A Comprehensive Survey and Benchmark](https://mlsanity.com/paper/2407.13278/) (2024)
- [Flow-of-Action: SOP Enhanced LLM-Based Multi-Agent System for Root Cause Analysis](https://mlsanity.com/paper/2502.08224/) (2025)
- [TimeSeriesBench: An Industrial-Grade Benchmark for Time Series Anomaly Detection Models](https://mlsanity.com/paper/2402.10802/) (2024)
- [KAN-AD: Time Series Anomaly Detection with Kolmogorov-Arnold Networks](https://mlsanity.com/paper/2411.00278/) (2024)
- [K2VAE: A Koopman-Kalman Enhanced Variational AutoEncoder for Probabilistic Time Series Forecasting](https://mlsanity.com/paper/2505.23017/) (2025)
- [Wavelet Scattering Transform and Fourier Representation for Offline Detection of Malicious Clients in Federated Learning](https://mlsanity.com/paper/2506.09674/) (2025)
- [UModel: An Agent-Ready Observability Data Modeling Method at Scale](https://mlsanity.com/paper/2606.04799/) (2026)
- [LLM Agents for Time-Series: A Survey](https://mlsanity.com/paper/2608.26226/) (2026)
- [Learning Latent Spaces for Domain Generalization in Time Series Forecasting](https://mlsanity.com/paper/2412.11171/) (2024)
- [BEAT: Balanced Frequency Adaptive Tuning for Long-Term Time-Series Forecasting](https://mlsanity.com/paper/2501.19065/) (2025)
- [A Split-Window Transformer for Multi-Model Sequence Spammer Detection using Multi-Model Variational Autoencoder](https://mlsanity.com/paper/2502.16483/) (2025)
- [Energy-Aware Pattern Disentanglement: A Generalizable Pattern Assisted Architecture for Multi-task Time Series Analysis](https://mlsanity.com/paper/2504.14209/) (2025)
- [ViTs: Teaching Machines to See Time Series Anomalies Like Human Experts](https://mlsanity.com/paper/2510.04710/) (2025)
- [LPCVAE: A Conditional VAE with Long-Term Dependency and Probabilistic Time-Frequency Fusion for Time Series Anomaly Detection](https://mlsanity.com/paper/2510.10915/) (2025)
- [Strong Linear Baselines Strike Back: Closed-Form Linear Models as Gaussian Process Conditional Density Estimators for TSAD](https://mlsanity.com/paper/2602.00672/) (2026)
- [LEFT: Learnable Fusion of Tri-view Tokens for Unsupervised Time Series Anomaly Detection](https://mlsanity.com/paper/2602.08638/) (2026)
- [Contextual and Seasonal LSTMs for Time Series Anomaly Detection](https://mlsanity.com/paper/2602.09690/) (2026)
- [Bridging Classification and Reconstruction: Cooperative Time Series Anomaly Detection](https://mlsanity.com/paper/2605.26193/) (2026)
- [CAAD: Causality-Aware Multivariate Time Series Anomaly Detection via Multi-Scale Alignment and Structural Causal Consistency](https://mlsanity.com/paper/2607.08555/) (2026)
- [Lightweight Multi-Scale Anomaly Detection for Resource-Constrained Edge Devices](https://mlsanity.com/paper/2607.12599/) (2026)
- [Structured Frequency-Domain Evidence for LLM-Based Time-Series Anomaly Detection](https://mlsanity.com/paper/2608.24113/) (2026)
- [DrafTS: Time-Aware Decomposition with Residual Correction for Time Series Modeling](https://mlsanity.com/paper/2609.33368/) (2026)
- [RIPPLE in Still Water: Zero-Shot Clustering in Federated Learning with Wavelet Scattering Transform](https://mlsanity.com/paper/2610.03054/) (2026)
- [WaSA: Wavelet Scattering Autoencoders for Unsupervised Offline Detection of Malicious Clients in Federated Learning](https://mlsanity.com/paper/2610.13186/) (2026)

## 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.