针对数据漂移下的异常检测难题，提出两级集成的变分自编码器方法。
Drift-Aware Variational Autoencoder-based Anomaly Detection with Two-level Ensembling
- 用多个变分自编码器构成第一级集成，联合预测异常
- 引入统计检测器组成第二级集成，实时捕捉概念漂移
- 在低异常率和强漂移场景下显著优于现有方法
在当今数字世界中，各领域持续生成海量流式数据，但多数数据无标签，导致异常事件识别困难。尤其在非平稳环境中，模型性能会因概念漂移随时间退化。为此，本文提出新方法 VAE++ESDD，结合增量学习与两级集成：第一级为多个变分自编码器（VAEs）的集成，用于异常预测；第二级为多个概念漂移检测器的集成，每个检测器采用基于统计的漂移机制。通过在真实与合成数据集上开展全面实验，这些数据具有严重或极低异常率及多种漂移特征，结果表明该方法显著优于多个强基线与先进方法。
原文摘要 · Abstract (English)
In today's digital world, the generation of vast amounts of streaming data in various domains has become ubiquitous. However, many of these data are unlabeled, making it challenging to identify events, particularly anomalies. This task becomes even more formidable in nonstationary environments where model performance can deteriorate over time due to concept drift. To address these challenges, this paper presents a novel method, VAE++ESDD, which employs incremental learning and two-level ensembling: an ensemble of Variational AutoEncoder(VAEs) for anomaly prediction, along with an ensemble of concept drift detectors. Each drift detector utilizes a statistical-based concept drift mechanism. To evaluate the effectiveness of VAE++ESDD, we conduct a comprehensive experimental study using real-world and synthetic datasets characterized by severely or extremely low anomalous rates and various drift characteristics. Our study reveals that the proposed method significantly outperforms both strong baselines and state-of-the-art methods.
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。