MuRAL-CPD: Active Learning for Multiresolution Change Point Detection

2026-01-28

AI Summary

This work proposes a semi-supervised change point detection framework that integrates active learning with multi-resolution analysis to address the limitations of existing unsupervised methods, which often fail to align with task-specific definitions of “change” and cannot incorporate user prior knowledge. By leveraging wavelet decomposition, the approach characterizes changes across multiple temporal scales and iteratively refines model hyperparameters through user feedback, thereby adaptively aligning with the semantic notion of change relevant to the application. The proposed method significantly enhances both detection accuracy and interpretability, outperforming state-of-the-art techniques on multiple real-world datasets—particularly in scenarios where only a minimal number of labeled samples are available.

Technology Category

• Machine Learning: Active Learning
• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Computer Vision: Video Understanding & Activity Analysis

Application Category

• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding

Abstract

Change Point Detection (CPD) is a critical task in time series analysis, aiming to identify moments when the underlying data-generating process shifts. Traditional CPD methods often rely on unsupervised techniques, which lack adaptability to task-specific definitions of change and cannot benefit from user knowledge. To address these limitations, we propose MuRAL-CPD, a novel semi-supervised method that integrates active learning into a multiresolution CPD algorithm. MuRAL-CPD leverages a wavelet-based multiresolution decomposition to detect changes across multiple temporal scales and incorporates user feedback to iteratively optimize key hyperparameters. This interaction enables the model to align its notion of change with that of the user, improving both accuracy and interpretability. Our experimental results on several real-world datasets show the effectiveness of MuRAL-CPD against state-of-the-art methods, particularly in scenarios where minimal supervision is available.

Problem

• Change Point Detection
• Active Learning
• Multiresolution
• Semi-supervised Learning
• Time Series Analysis

Innovation

• active learning
• multiresolution
• change point detection
• wavelet decomposition
• semi-supervised