TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Data

TL;DR

TranAD introduces a transformer-based anomaly detection model for multivariate time series that achieves high accuracy and efficiency, outperforming existing methods in detection and diagnosis with limited data and reduced training time.

Contribution

The paper presents TranAD, a novel transformer network utilizing attention mechanisms, self-conditioning, adversarial training, and meta-learning for robust, fast, and data-efficient anomaly detection.

Findings

Outperforms state-of-the-art methods in F1 score by up to 17%.

Reduces training time by up to 99%.

Effective in limited data scenarios across multiple datasets.

Abstract

Efficient anomaly detection and diagnosis in multivariate time-series data is of great importance for modern industrial applications. However, building a system that is able to quickly and accurately pinpoint anomalous observations is a challenging problem. This is due to the lack of anomaly labels, high data volatility and the demands of ultra-low inference times in modern applications. Despite the recent developments of deep learning approaches for anomaly detection, only a few of them can address all of these challenges. In this paper, we propose TranAD, a deep transformer network based anomaly detection and diagnosis model which uses attention-based sequence encoders to swiftly perform inference with the knowledge of the broader temporal trends in the data. TranAD uses focus score-based self-conditioning to enable robust multi-modal feature extraction and adversarial training to gain stability. Additionally, model-agnostic meta learning (MAML) allows us to train the model using limited data. Extensive empirical studies on six publicly available datasets demonstrate that TranAD can outperform state-of-the-art baseline methods in detection and diagnosis performance with data and time-efficient training. Specifically, TranAD increases F1 scores by up to 17%, reducing training times by up to 99% compared to the baselines.