Improving Robustness on Seasonality-Heavy Multivariate Time Series
Anomaly Detection
- URL: http://arxiv.org/abs/2007.14254v1
- Date: Sat, 25 Jul 2020 01:32:00 GMT
- Title: Improving Robustness on Seasonality-Heavy Multivariate Time Series
Anomaly Detection
- Authors: Farzaneh Khoshnevisan, Zhewen Fan, Vitor R. Carvalho
- Abstract summary: This paper explores some of the challenges in Robust Anomaly Detection (AD) on time series data.
We propose a new approach that makes inroads towards increased robustness on seasonal and contaminated data.
We conduct extensive experiments in which not only do this model displays more robust behavior on complex seasonality patterns, but also shows increased resistance to training data contamination.
- Score: 2.2559617939136505
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Robust Anomaly Detection (AD) on time series data is a key component for
monitoring many complex modern systems. These systems typically generate
high-dimensional time series that can be highly noisy, seasonal, and
inter-correlated. This paper explores some of the challenges in such data, and
proposes a new approach that makes inroads towards increased robustness on
seasonal and contaminated data, while providing a better root cause
identification of anomalies. In particular, we propose the use of Robust
Seasonal Multivariate Generative Adversarial Network (RSM-GAN) that extends
recent advancements in GAN with the adoption of convolutional-LSTM layers and
attention mechanisms to produce excellent performance on various settings. We
conduct extensive experiments in which not only do this model displays more
robust behavior on complex seasonality patterns, but also shows increased
resistance to training data contamination. We compare it with existing
classical and deep-learning AD models, and show that this architecture is
associated with the lowest false positive rate and improves precision by 30%
and 16% in real-world and synthetic data, respectively.
Related papers
- GenIAS: Generator for Instantiating Anomalies in time Series [54.959865643340535]
We develop a generative model for time series anomaly detection (TSAD) using a variational autoencoder.
GenIAS is designed to produce diverse and realistic synthetic anomalies for TSAD tasks.
Our experiments demonstrate that GenIAS consistently outperforms seventeen traditional and deep anomaly detection models.
arXiv Detail & Related papers (2025-02-12T10:10:04Z) - Self-Supervised Learning for Time Series: A Review & Critique of FITS [0.0]
Recently proposed model, FITS, claims competitive performance with significantly reduced parameter counts.
By training a one-layer neural network in the complex frequency domain, we are able to replicate these results.
Our experiments reveal that FITS especially excels at capturing periodic and seasonal patterns, but struggles with trending, non-periodic, or random-resembling behavior.
arXiv Detail & Related papers (2024-10-23T23:03:09Z) - SFANet: Spatial-Frequency Attention Network for Weather Forecasting [54.470205739015434]
Weather forecasting plays a critical role in various sectors, driving decision-making and risk management.
Traditional methods often struggle to capture the complex dynamics of meteorological systems.
We propose a novel framework designed to address these challenges and enhance the accuracy of weather prediction.
arXiv Detail & Related papers (2024-05-29T08:00:15Z) - Revisiting VAE for Unsupervised Time Series Anomaly Detection: A
Frequency Perspective [40.21603048003118]
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.
arXiv Detail & Related papers (2024-02-05T09:06:57Z) - DACR: Distribution-Augmented Contrastive Reconstruction for Time-Series
Anomaly Detection [12.3866167448478]
Anomaly detection in time-series data is crucial for identifying faults, failures, threats, and outliers across a range of applications.
Recently, deep learning techniques have been applied to this topic, but they often struggle in real-world scenarios.
We propose Distribution-Augmented Contrastive Reconstruction (DACR) to tackle these challenges.
arXiv Detail & Related papers (2024-01-20T16:56:52Z) - 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) - MADS: Modulated Auto-Decoding SIREN for time series imputation [9.673093148930874]
We propose MADS, a novel auto-decoding framework for time series imputation, built upon implicit neural representations.
We evaluate our model on two real-world datasets, and show that it outperforms state-of-the-art methods for time series imputation.
arXiv Detail & Related papers (2023-07-03T09:08:47Z) - Generative Time Series Forecasting with Diffusion, Denoise, and
Disentanglement [51.55157852647306]
Time series forecasting has been a widely explored task of great importance in many applications.
It is common that real-world time series data are recorded in a short time period, which results in a big gap between the deep model and the limited and noisy time series.
We propose to address the time series forecasting problem with generative modeling and propose a bidirectional variational auto-encoder equipped with diffusion, denoise, and disentanglement.
arXiv Detail & Related papers (2023-01-08T12:20:46Z) - HIFI: Anomaly Detection for Multivariate Time Series with High-order
Feature Interactions [7.016615391171876]
HIFI builds multivariate feature interaction graph automatically and uses the graph convolutional neural network to achieve high-order feature interactions.
Experiments on three publicly available datasets demonstrate the superiority of our framework compared with state-of-the-art approaches.
arXiv Detail & Related papers (2021-06-11T04:57:03Z) - 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) - Transformer Hawkes Process [79.16290557505211]
We propose a Transformer Hawkes Process (THP) model, which leverages the self-attention mechanism to capture long-term dependencies.
THP outperforms existing models in terms of both likelihood and event prediction accuracy by a notable margin.
We provide a concrete example, where THP achieves improved prediction performance for learning multiple point processes when incorporating their relational information.
arXiv Detail & Related papers (2020-02-21T13:48:13Z)
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.