Cross-Domain Contrastive Learning for Time Series Clustering
Open Access
- 24 March 2024
- journal article
- research article
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38 (8) , 8921-8929
Abstract
Most deep learning-based time series clustering models concentrate on data representation in a separate process from clustering. This leads to that clustering loss cannot guide feature extraction. Moreover, most methods solely analyze data from the temporal domain, disregarding the potential within the frequency domain. To address these challenges, we introduce a novel end-to-end Cross-Domain Contrastive learning model for time series Clustering (CDCC). Firstly, it integrates the clustering process and feature extraction using contrastive constraints at both cluster-level and instance-level. Secondly, the data is encoded simultaneously in both temporal and frequency domains, leveraging contrastive learning to enhance within-domain representation. Thirdly, cross-domain constraints are proposed to align the latent representations and category distribution across domains. With the above strategies, CDCC not only achieves end-to-end output but also effectively integrates frequency domains. Extensive experiments and visualization analysis are conducted on 40 time series datasets from UCR, demonstrating the superior performance of the proposed model.Keywords
This publication has 10 references indexed in Scilit:
- TCGAN: Convolutional Generative Adversarial Network for time series classification and clusteringNeural Networks, 2023
- Multiview Unsupervised Shapelet Learning for Multivariate Time Series ClusteringIEEE Transactions on Pattern Analysis and Machine Intelligence, 2022
- Deep Time-Series Clustering: A ReviewElectronics, 2021
- Integrated Generative Model for Industrial Anomaly Detection via Bidirectional LSTM and Attention MechanismIEEE Transactions on Industrial Informatics, 2021
- Self-Supervised Time Series Clustering With Model-Based DynamicsIEEE Transactions on Neural Networks and Learning Systems, 2020
- The UCR time series archiveIEEE/CAA Journal of Automatica Sinica, 2019
- Short-Term Traffic Prediction Based on DeepCluster in Large-Scale Road NetworksIEEE Transactions on Vehicular Technology, 2019
- Cluster’s Quality Evaluation and Selective Clustering EnsembleACM Transactions on Knowledge Discovery From Data, 2018
- Time-series clustering – A decade reviewInformation Systems, 2015
- Using derivatives in a longest common subsequence dissimilarity measure for time series classificationPattern Recognition Letters, 2014