用xLSTM构建首个时间序列异常检测模型，效果超越23种主流方法。
xLSTMAD: A Powerful xLSTM-based Method for Anomaly Detection
- 采用编码器-解码器xLSTM架构，分别通过预测和重构两种方式捕捉时序特征。
- 在17个真实数据集上使用VUS-PR指标，性能超越23个基准模型，最佳结果提升达8.7%。
- 支持多变量时序，适合工业监控、金融风控等需要高精度异常识别的场景。
最近提出的xLSTM是一种强大的模型，利用高效的乘法门控与残差连接，具备长时序建模能力，在时间序列预测、无损压缩及大规模语言建模中表现优异，其线性内存占用和快速推理使其成为Transformer的可行替代方案。尽管日益流行，但此前尚无研究将xLSTM用于异常检测。本文首次提出xLSTMAD，一个专为多变量时间序列设计的完整编码器-解码器xLSTM异常检测方法。编码器捕获历史上下文，解码器分为两种变体：预测式（xLSTMAD-F）迭代生成未来值，重构式（xLSTMAD-R）从编码表示重建输入序列。我们对比了均方误差（MSE）与软动态时间规整（SoftDTW）两种损失函数，分别关注局部重建精度与全局序列对齐。在涵盖17个真实世界数据集的TSB-AD-M基准上，使用VUS-PR等先进指标评估，xLSTMAD展现业界领先性能，显著优于23种主流异常检测基线。本工作首次揭示xLSTM在异常检测中的强大建模潜力，为该领域开启新方向。代码已开源：https://github.com/Nyderx/xlstmad
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。