TimeCSL: Unsupervised Contrastive Learning of General Shapelets for Explorable Time Series Analysis

Summary: CSL: the first unsupervised contrastive learner of general, interpretable shapelet-based time-series representations, improving classification, clustering, and anomaly detection. TimeCSL: an end-to-end interactive system to explore learned shapelets for unified analysis. (summarized by gpt-5-mini on Feb 09 2026)

Paper ID: hadb776063b6f2c48
Venue: VLDB
Year: 2024
Pagerank: 5.1176637e-05
Overall Rank: 9,873 | 33.62%
DOI: 10.14778/3685800.3685907

Incoming Non-self Citations Over Time

Authors

1. Zhiyu Liang (Harbin Engineering University)
2. Chen Liang (Harbin Engineering University)
3. Zheng Liang (Harbin Engineering University)
4. Hongzhi Wang (Harbin Engineering University)
5. Bo Zheng (CnosDB Inc.)

BibTeX Citation

@article{liang_vldb24,
        title = {{TimeCSL: Unsupervised Contrastive Learning of General Shapelets for Explorable Time Series Analysis}},
        author = {Liang, Zhiyu and Liang, Chen and Liang, Zheng and Wang, Hongzhi and Zheng, Bo},
        journal = {PVLDB},
        series = {{VLDB} '24},
        volume = {17},
        number = {12},
        pages = {4489--4492},
        doi = {10.14778/3685800.3685907},
        url = {https://doi.org/10.14778/3685800.3685907},
        year = {2024}
}

Incoming Citations (Sorted by Pagerank)

Showing 2 of 2 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
10,535	SWIFT: Enabling Large-Scale Temporal Graph Learning on a Single Machine	2026	SIGMOD	4.9793485e-05
10,760	KDSelector: A Framework of Knowledge-Enhanced and Data-Efficient Selector Learning for Anomaly Detection Model Selection in Time Series	2026	VLDB	4.9793485e-05

Outgoing Citations (Sorted by Pagerank)

Showing 1 of 1 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank	Cited Paper	Year	Venue	Pagerank
13,677	A Shapelet-based Framework for Unsupervised Multivariate Time Series Representation Learning	2024	VLDB	-

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	3,726	Choose Wisely: An Extensive Evaluation of Model Selection for Anomaly Detection in Time Series	2023	VLDB
2	9,482	TSB-AutoAD: Towards Automated Solutions for Time-Series Anomaly Detection	2025	VLDB
3	7,763	OneShotSTL: One-Shot Seasonal-Trend Decomposition For Online Time Series Anomaly Detection And Forecasting	2023	VLDB
4	4,966	Unsupervised Time Series Outlier Detection with Diversity-Driven Convolutional Ensembles	2022	VLDB
5	11,054	CLaP - State Detection from Time Series	2026	VLDB
6	3,990	Time2Feat: Learning Interpretable Representations for Multivariate Time Series Clustering	2023	VLDB
7	6,073	AutoTSAD: Unsupervised Holistic Anomaly Detection for Time Series Data	2024	VLDB
8	7,094	Time-Series Clustering: A Comprehensive Study of Data Mining, Machine Learning, and Deep Learning Methods	2025	VLDB
9	9,489	Time2State: An Unsupervised Framework for Inferring the Latent States in Time Series Data	2023	SIGMOD
10	13,677	A Shapelet-based Framework for Unsupervised Multivariate Time Series Representation Learning	2024	VLDB