Multivariate Time-series Anomaly Detection via Dynamic Model Pool & Ensembling

TL;DR

This paper introduces DMPEAD, a dynamic ensemble framework for multivariate time-series anomaly detection that adaptively constructs and updates a diverse model pool, significantly improving performance and scalability over existing methods.

Contribution

The paper presents a novel dynamic model pool and ensembling framework that adaptively updates models for improved multivariate time-series anomaly detection.

Findings

Outperforms all baseline methods on 8 real-world datasets

Demonstrates superior adaptability to data changes

Shows enhanced scalability with high-dimensional data

Abstract

Multivariate time-series (MTS) anomaly detection is critical in domains such as service monitor, IoT, and network security. While multi-model methods based on selection or ensembling outperform single-model ones, they still face limitations: (i) selection methods rely on a single chosen model and are sensitive to the strategy; (ii) ensembling methods often combine all models or are restricted to univariate data; and (iii) most methods depend on fixed data dimensionality, limiting scalability. To address these, we propose DMPEAD, a Dynamic Model Pool and Ensembling framework for MTS Anomaly Detection. The framework first (i) constructs a diverse model pool via parameter transfer and diversity metric, then (ii) updates it with a meta-model and similarity-based strategy for adaptive pool expansion, subset selection, and pool merging, finally (iii) ensembles top-ranked models through proxy metric ranking and top-k aggregation in the selected subset, outputting the final anomaly detection result. Extensive experiments on 8 real-world datasets show that our model outperforms all baselines, demonstrating superior adaptability and scalability.