无需修改模型结构，就能提升时间序列异常检测效果。
MADCluster: Model-agnostic Anomaly Detection with Self-supervised Clustering Network
- 用自监督聚类将正常数据压缩到一个中心点，避免传统方法的球形坍塌问题。
- 在4个时间序列基准数据集上，相比基线模型，平均性能提升超过10%。
- 适合想快速增强现有模型异常检测能力的研究者和工程师使用。
本文提出MADCluster，一种无需依赖特定模型架构的时间序列异常检测框架，通过自监督聚类解决现有深度学习方法中固有的‘超球坍塌’问题。核心思想是将正常模式数据聚为单一簇，同时学习簇中心并映射数据靠近该中心。为此，提出新的‘单向自适应损失’，其优化过程已数学证明。MADCluster包含三个组件：捕获高维时序动态的基底嵌入器、簇距离映射模块、以及用于持续更新中心的序列级聚类。通过在不同基底嵌入器上的应用，实现模型无关性。在四个时间序列基准数据集上的实验表明，MADCluster能显著提升对比模型的整体性能，验证了其跨架构兼容性的潜力。
原文摘要 · Abstract (English)
In this paper, we propose MADCluster, a novel model-agnostic anomaly detection framework utilizing self-supervised clustering. MADCluster is applicable to various deep learning architectures and addresses the 'hypersphere collapse' problem inherent in existing deep learning-based anomaly detection methods. The core idea is to cluster normal pattern data into a 'single cluster' while simultaneously learning the cluster center and mapping data close to this center. Also, to improve expressiveness and enable effective single clustering, we propose a new 'One-directed Adaptive loss'. The optimization of this loss is mathematically proven. MADCluster consists of three main components: Base Embedder capturing high-dimensional temporal dynamics, Cluster Distance Mapping, and Sequence-wise Clustering for continuous center updates. Its model-agnostic characteristics are achieved by applying various architectures to the Base Embedder. Experiments on four time series benchmark datasets demonstrate that applying MADCluster improves the overall performance of comparative models. In conclusion, the compatibility of MADCluster shows potential for enhancing model performance across various architectures.
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。