Cross-Domain Contrastive Learning for Time Series Clustering
DOI:
https://doi.org/10.1609/aaai.v38i8.28740Keywords:
DMKM: Data Stream Mining, DMKM: Data Visualization & SummarizationAbstract
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.Downloads
Published
2024-03-24
How to Cite
Peng, F., Luo, J., Lu, X., Wang, S., & Li, F. (2024). Cross-Domain Contrastive Learning for Time Series Clustering. Proceedings of the AAAI Conference on Artificial Intelligence, 38(8), 8921-8929. https://doi.org/10.1609/aaai.v38i8.28740
Issue
Section
AAAI Technical Track on Data Mining & Knowledge Management