KDSelector: A Knowledge-Enhanced and Data-Efficient Model Selector Learning Framework for Time Series Anomaly Detection

2025-03-16

AI Summary

Addressing the challenges of model selection difficulty, insufficient exploitation of historical knowledge, and low training efficiency in time-series anomaly detection (TSAD), this paper proposes a novel, knowledge-enhanced and data-efficient neural network selector framework. Methodologically, it introduces a knowledge injection mechanism—integrating knowledge distillation with temporal feature disentanglement—and a dynamic sample pruning strategy based on importance-aware sampling and meta-learning, enabling plug-and-play deployment without modifying downstream TSAD models. The framework significantly improves selector accuracy and training efficiency: on diverse real-world time-series benchmarks, it achieves an average 12.7% gain in selection accuracy and reduces training time by 43%, while demonstrating superior generalization over existing state-of-the-art methods.

Technology Category

• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Machine Learning: Time-Series/Data Streams
• Search and Optimization: Learning to Search

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Model selection has been raised as an essential problem in the area of time series anomaly detection (TSAD), because there is no single best TSAD model for the highly heterogeneous time series in real-world applications. However, despite the success of existing model selection solutions that train a classification model (especially neural network, NN) using historical data as a selector to predict the correct TSAD model for each series, the NN-based selector learning methods used by existing solutions do not make full use of the knowledge in the historical data and require iterating over all training samples, which limits the accuracy and training speed of the selector. To address these limitations, we propose KDSelector, a novel knowledge-enhanced and data-efficient framework for learning the NN-based TSAD model selector, of which three key components are specifically designed to integrate available knowledge into the selector and dynamically prune less important and redundant samples during the learning. We develop a TSAD model selection system with KDSelector as the internal, to demonstrate how users improve the accuracy and training speed of their selectors by using KDSelector as a plug-and-play module. Our demonstration video is hosted at https://youtu.be/2uqupDWvTF0.

Problem

• Improves model selection accuracy for time series anomaly detection
• Enhances training speed by dynamically pruning redundant samples
• Integrates historical knowledge into neural network-based selectors

Innovation

• Integrates knowledge into neural network selectors
• Dynamically prunes redundant training samples
• Enhances selector accuracy and training speed