论文标题
具有隐式神经表示的时间序列异常检测
Time-Series Anomaly Detection with Implicit Neural Representation
论文作者
论文摘要
在许多实际应用中，在多元时间序列数据中检测异常是必不可少的。最近，各种基于深度学习的方法显示了时间序列异常检测的大量改善。但是，现有方法仍然存在几个限制，例如由于其复杂的模型设计或昂贵的调整程序，以找到给定数据集的最佳超参数（例如，滑动窗口长度）。在我们的论文中，我们提出了一种称为隐式神经表示基于隐性异常检测（INRAD）的新方法。具体而言，我们训练一个简单的多层感知器，该透视时间花费时间为输入，并在当时输出相应的值。然后，我们利用表示误差作为检测异常的异常得分。五个现实世界数据集的实验表明，我们所提出的方法在性能，训练速度和鲁棒性方面优于其他最先进的方法。
Detecting anomalies in multivariate time-series data is essential in many real-world applications. Recently, various deep learning-based approaches have shown considerable improvements in time-series anomaly detection. However, existing methods still have several limitations, such as long training time due to their complex model designs or costly tuning procedures to find optimal hyperparameters (e.g., sliding window length) for a given dataset. In our paper, we propose a novel method called Implicit Neural Representation-based Anomaly Detection (INRAD). Specifically, we train a simple multi-layer perceptron that takes time as input and outputs corresponding values at that time. Then we utilize the representation error as an anomaly score for detecting anomalies. Experiments on five real-world datasets demonstrate that our proposed method outperforms other state-of-the-art methods in performance, training speed, and robustness.
