Time Series Change Point Detection with Self-Supervised Contrastive Predictive Coding

Abstract

Change Point Detection (CPD) methods identify the times associated with changes in the trends and properties of time series data in order to describe the underlying behaviour of the system. For instance, detecting the changes and anomalies associated with web service usage, application usage or human behaviour can provide valuable insights for downstream modelling tasks. We propose a novel approach for self-supervised Time Series Change Point detection method based onContrastivePredictive coding (TS-CP^2). TS-CP^2 is the first approach to employ a contrastive learning strategy for CPD by learning an embedded representation that separates pairs of embeddings of time adjacent intervals from pairs of interval embeddings separated across time. Through extensive experiments on three diverse, widely used time series datasets, we demonstrate that our method outperforms five state-of-the-art CPD methods, which include unsupervised and semi-supervisedapproaches. TS-CP^2 is shown to improve the performance of methods that use either handcrafted statistical or temporal features by 79.4% and deep learning-based methods by 17.0% with respect to the F1-score averaged across the three datasets.

Accepted at The WEB Conference 2021 (WWW'21)

References in corpus (5)

• FaceNet: A Unified Embedding for Face Recognition and Clustering
• Change-Point Detection in Time-Series Data by Relative Density-Ratio Estimation
• Multi-task Self-Supervised Learning for Human Activity Detection
• Joint segmentation of multivariate time series with hidden process regression for human activity recognition
• ESPRESSO: Entropy and ShaPe awaRe timE-Series SegmentatiOn for processing heterogeneous sensor data

Cited by in corpus (8)

• DCdetector: Dual Attention Contrastive Representation Learning for Time Series Anomaly Detection
• COCOA: Cross Modality Contrastive Learning for Sensor Data
• Evaluating Large Language Models as Virtual Annotators for Time-series Physical Sensing Data
• Online Neural Networks for Change-Point Detection
• Multiscale Representation Enhanced Temporal Flow Fusion Model for Long-Term Workload Forecasting
• Fast and Multi-aspect Mining of Complex Time-stamped Event Streams
• A Hierarchical Framework with Spatio-Temporal Consistency Learning for Emergence Detection in Complex Adaptive Systems
• Revisiting Backdoor Attacks on Time Series Classification in the Frequency Domain