TransNAS-TSAD: Harnessing Transformers for Multi-Objective Neural Architecture Search in Time Series Anomaly Detection

TL;DR

TransNAS-TSAD introduces a transformer-based neural architecture search framework optimized with NSGA-II, achieving superior anomaly detection in time series data by balancing accuracy and computational efficiency.

Contribution

The paper presents a novel NAS framework combining transformers and multi-objective optimization for time series anomaly detection, setting new performance benchmarks.

Findings

Outperforms traditional anomaly detection models

Introduces the EACS metric for balanced evaluation

Demonstrates versatility across diverse data scenarios

Abstract

The surge in real-time data collection across various industries has underscored the need for advanced anomaly detection in both univariate and multivariate time series data. This paper introduces TransNAS-TSAD, a framework that synergizes the transformer architecture with neural architecture search (NAS), enhanced through NSGA-II algorithm optimization. This approach effectively tackles the complexities of time series data, balancing computational efficiency with detection accuracy. Our evaluation reveals that TransNAS-TSAD surpasses conventional anomaly detection models due to its tailored architectural adaptability and the efficient exploration of complex search spaces, leading to marked improvements in diverse data scenarios. We also introduce the Efficiency-Accuracy-Complexity Score (EACS) as a new metric for assessing model performance, emphasizing the balance between accuracy and computational resources. TransNAS-TSAD sets a new benchmark in time series anomaly detection, offering a versatile, efficient solution for complex real-world applications. This research highlights the TransNAS-TSAD potential across a wide range of industry applications and paves the way for future developments in the field.