xLSTMAD: A Powerful xLSTM-based Method for Anomaly Detection

TL;DR

This paper introduces xLSTMAD, a novel anomaly detection method using an xLSTM encoder-decoder architecture tailored for multivariate time series, demonstrating state-of-the-art performance on a comprehensive benchmark.

Contribution

First to adapt xLSTM for anomaly detection, integrating encoder-decoder architecture with multiple loss functions, and validating its effectiveness on extensive real-world datasets.

Findings

xLSTMAD outperforms 23 baseline methods in anomaly detection accuracy.

The method achieves state-of-the-art results on the TSB-AD-M benchmark.

Both MSE and SoftDTW loss functions effectively enhance detection performance.

Abstract

The recently proposed xLSTM is a powerful model that leverages expressive multiplicative gating and residual connections, providing the temporal capacity needed for long-horizon forecasting and representation learning. This architecture has demonstrated success in time series forecasting, lossless compression, and even large-scale language modeling tasks, where its linear memory footprint and fast inference make it a viable alternative to Transformers. Despite its growing popularity, no prior work has explored xLSTM for anomaly detection. In this work, we fill this gap by proposing xLSTMAD, the first anomaly detection method that integrates a full encoder-decoder xLSTM architecture, purpose-built for multivariate time series data. Our encoder processes input sequences to capture historical context, while the decoder is devised in two separate variants of the method. In the forecasting approach, the decoder iteratively generates forecasted future values xLSTMAD-F, while the reconstruction approach reconstructs the input time series from its encoded counterpart xLSTMAD-R. We investigate the performance of two loss functions: Mean Squared Error (MSE), and Soft Dynamic Time Warping (SoftDTW) to consider local reconstruction fidelity and global sequence alignment, respectively. We evaluate our method on the comprehensive TSB-AD-M benchmark, which spans 17 real-world datasets, using state-of-the-art challenging metrics such as VUS-PR. In our results, xLSTM showcases state-of-the-art accuracy, outperforming 23 popular anomaly detection baselines. Our paper is the first work revealing the powerful modeling capabilities of xLSTM for anomaly detection, paving the way for exciting new developments on this subject. Our code is available at: https://github.com/Nyderx/xlstmad