A Shapelet-based Framework for Unsupervised Multivariate Time Series Representation Learning
Summary: First unsupervised multivariate time-series URL using shapelet-based embeddings via contrastive learning. Uses a unified shapelet encoder with multi-grained contrast, multi-scale alignment and augmentations, outperforming URL and task-specific baselines on many datasets. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Zhiyu Liang
- 2. Jianfeng Zhang
- 3. Chen Liang
- 4. Hongzhi Wang
- 5. Zheng Liang
- 6. Lujia Pan
Incoming Citations (Sorted by Pagerank)
Showing 2 of 2 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 9,559 | TimeCSL: Unsupervised Contrastive Learning of General Shapelets for Explorable Time Series Analysis | 2024 | VLDB | 4.3254416e-05 |
| 10,441 | KDSelector: A Knowledge-Enhanced and Data-Efficient Model Selector Learning Framework for Time Series Anomaly Detection | 2025 | SIGMOD | 4.1945683e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 0 of 0 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next