Revisiting VAE for Unsupervised Time Series Anomaly Detection: A
Frequency Perspective
- URL: http://arxiv.org/abs/2402.02820v1
- Date: Mon, 5 Feb 2024 09:06:57 GMT
- Title: Revisiting VAE for Unsupervised Time Series Anomaly Detection: A
Frequency Perspective
- Authors: Zexin Wang, Changhua Pei, Minghua Ma, Xin Wang, Zhihan Li, Dan Pei,
Saravan Rajmohan, Dongmei Zhang, Qingwei Lin, Haiming Zhang, Jianhui Li,
Gaogang Xie
- Abstract summary: Variational Autoencoders (VAEs) have gained popularity in recent decades due to their superior de-noising capabilities.
FCVAE exploits an innovative approach to concurrently integrate both the global and local frequency features into the condition of Conditional Variational Autoencoder (CVAE)
Our approach has been evaluated on public datasets and a large-scale cloud system, and the results demonstrate that it outperforms state-of-the-art methods.
- Score: 40.21603048003118
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: 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.
Related papers
- PeFAD: A Parameter-Efficient Federated Framework for Time Series Anomaly Detection [51.20479454379662]
We propose a.
Federated Anomaly Detection framework named PeFAD with the increasing privacy concerns.
We conduct extensive evaluations on four real datasets, where PeFAD outperforms existing state-of-the-art baselines by up to 28.74%.
arXiv Detail & Related papers (2024-06-04T13:51:08Z) - Graph Spatiotemporal Process for Multivariate Time Series Anomaly
Detection with Missing Values [67.76168547245237]
We introduce a novel framework called GST-Pro, which utilizes a graphtemporal process and anomaly scorer to detect anomalies.
Our experimental results show that the GST-Pro method can effectively detect anomalies in time series data and outperforms state-of-the-art methods.
arXiv Detail & Related papers (2024-01-11T10:10:16Z) - Video Anomaly Detection via Spatio-Temporal Pseudo-Anomaly Generation : A Unified Approach [49.995833831087175]
This work proposes a novel method for generating generic Video-temporal PAs by inpainting a masked out region of an image.
In addition, we present a simple unified framework to detect real-world anomalies under the OCC setting.
Our method performs on par with other existing state-of-the-art PAs generation and reconstruction based methods under the OCC setting.
arXiv Detail & Related papers (2023-11-27T13:14:06Z) - Explainable Time Series Anomaly Detection using Masked Latent Generative Modeling [1.3927943269211591]
We present TimeVQVAE-AD, a novel time series anomaly detection method.
TimeVQVAE-AD achieves excellent detection accuracy while offering a superior level of explainability.
We provide our implementation on GitHub.
arXiv Detail & Related papers (2023-11-21T11:59:16Z) - ImDiffusion: Imputed Diffusion Models for Multivariate Time Series
Anomaly Detection [44.21198064126152]
We propose a novel anomaly detection framework named ImDiffusion.
ImDiffusion combines time series imputation and diffusion models to achieve accurate and robust anomaly detection.
We evaluate the performance of ImDiffusion via extensive experiments on benchmark datasets.
arXiv Detail & Related papers (2023-07-03T04:57:40Z) - TFAD: A Decomposition Time Series Anomaly Detection Architecture with
Time-Frequency Analysis [12.867257563413972]
Time series anomaly detection is a challenging problem due to the complex temporal dependencies and the limited label data.
We propose a Time-Frequency analysis based time series Anomaly Detection model, or TFAD, to exploit both time and frequency domains for performance improvement.
arXiv Detail & Related papers (2022-10-18T09:08:57Z) - TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate
Time Series Data [13.864161788250856]
TranAD is a deep transformer network based anomaly detection and diagnosis model.
It uses attention-based sequence encoders to swiftly perform inference with the knowledge of the broader temporal trends in the data.
TranAD can outperform state-of-the-art baseline methods in detection and diagnosis performance with data and time-efficient training.
arXiv Detail & Related papers (2022-01-18T19:41:29Z) - DAE : Discriminatory Auto-Encoder for multivariate time-series anomaly
detection in air transportation [68.8204255655161]
We propose a novel anomaly detection model called Discriminatory Auto-Encoder (DAE)
It uses the baseline of a regular LSTM-based auto-encoder but with several decoders, each getting data of a specific flight phase.
Results show that the DAE achieves better results in both accuracy and speed of detection.
arXiv Detail & Related papers (2021-09-08T14:07:55Z) - TadGAN: Time Series Anomaly Detection Using Generative Adversarial
Networks [73.01104041298031]
TadGAN is an unsupervised anomaly detection approach built on Generative Adversarial Networks (GANs)
To capture the temporal correlations of time series, we use LSTM Recurrent Neural Networks as base models for Generators and Critics.
To demonstrate the performance and generalizability of our approach, we test several anomaly scoring techniques and report the best-suited one.
arXiv Detail & Related papers (2020-09-16T15:52:04Z)
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.