KDSelector: A Knowledge-Enhanced and Data-Efficient Model Selector Learning Framework for Time Series Anomaly Detection
Summary: KDSelector: a knowledge-infused, data-efficient NN-based TSAD model selector; tackles heterogeneity by avoiding a single winner. It uses history-derived knowledge and selective pruning to speed training and boost selector accuracy as a plug-in module. (summarized by gpt-5-nano 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 (Harbin Engineering University)
- 2. Dongrui Cai (Harbin Engineering University)
- 3. Chenyuan Zhang (Harbin Engineering University)
- 4. Zheng Liang (Harbin Engineering University)
- 5. Chen Liang (Harbin Engineering University)
- 6. Bo Zheng (CnosDB Inc.)
- 7. Shi Qiu (Central South University)
- 8. Jin Wang (Central South University)
- 9. Hongzhi Wang (Harbin Engineering University)
BibTeX Citation
@inproceedings{liang_sigmod25,
title = {{KDSelector: A Knowledge-Enhanced and Data-Efficient Model Selector Learning Framework for Time Series Anomaly Detection}},
author = {Liang, Zhiyu and Cai, Dongrui and Zhang, Chenyuan and Liang, Zheng and Liang, Chen and Zheng, Bo and Qiu, Shi and Wang, Jin and Wang, Hongzhi},
series = {{SIGMOD} '25},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3722212.3725110},
url = {https://dl.acm.org/doi/10.1145/3722212.3725110},
year = {2025}
}Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 3 of 3 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 1,029 | Anomaly Detection in Time Series: A Comprehensive Evaluation | 2022 | VLDB | 0.00012557065 |
| 3,987 | Choose Wisely: An Extensive Evaluation of Model Selection for Anomaly Detection in Time Series | 2023 | VLDB | 6.9722766e-05 |
| 13,360 | A Shapelet-based Framework for Unsupervised Multivariate Time Series Representation Learning | 2024 | VLDB | - |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 11,099 | MLP-Mixer based Masked Autoencoders Are Effective, Explainable and Robust for Time Series Anomaly Detection | 2025 | VLDB |
| 2 | 8,229 | Mining Approximate Top-K Subspace Anomalies in Multi-Dimensional Time-Series Data | 2007 | VLDB |
| 3 | 9,382 | TAB: Unified Benchmarking of Time Series Anomaly Detection Methods | 2025 | VLDB |
| 4 | 11,300 | Time-Series Anomaly Detection: Overview and New Trends | 2024 | VLDB |
| 5 | 6,141 | An Experimental Evaluation of Anomaly Detection in Time Series | 2024 | VLDB |
| 6 | 11,056 | EasyAD: A Demonstration of Automated Solutions for Time-Series Anomaly Detection | 2025 | VLDB |
| 7 | 1,029 | Anomaly Detection in Time Series: A Comprehensive Evaluation | 2022 | VLDB |
| 8 | 5,986 | AutoTSAD: Unsupervised Holistic Anomaly Detection for Time Series Data | 2024 | VLDB |
| 9 | 10,977 | TSB-AutoAD: Towards Automated Solutions for Time-Series Anomaly Detection | 2025 | VLDB |
| 10 | 3,987 | Choose Wisely: An Extensive Evaluation of Model Selection for Anomaly Detection in Time Series | 2023 | VLDB |