mlsanityData to 7 Oct 2026

FedST: Secure Federated Shapelet Transformation for Time Series Classification

arXiv 2302.10631 ↗First posted 21 Feb 2023cs.LG cs.DBcited by 1

Not on the map. Why?

Abstract (arXiv)

This paper explores how to build a shapelet-based time series classification (TSC) model in the federated learning (FL) scenario, that is, using more data from multiple owners without actually sharing the data. We propose FedST, a novel federated TSC framework extended from a centralized shapelet transformation method. We recognize the federated shapelet search step as the kernel of FedST. Thus, we design a basic protocol for the FedST kernel that we prove to be secure and accurate. However, we identify that the basic protocol suffers from efficiency bottlenecks and the centralized acceleration techniques lose their efficacy due to the security issues. To speed up the federated protocol with security guarantee, we propose several optimizations tailored for the FL setting. Our theoretical analysis shows that the proposed methods are secure and more efficient. We conduct extensive experiments using both synthetic and real-world datasets. Empirical results show that our FedST solution is effective in terms of TSC accuracy, and the proposed optimizations can achieve three orders of magnitude of speedup.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 37 of its 112 references that are in the map. First posted on arXiv 21 Feb 2023.

Builds on

37 of 112 references.

References · 37

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2019Advances and Open Problems in Federated Learningcited by 3,021
  3. 2016Deep Learning with Differential Privacycited by 2,682
  4. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,531
  5. 2017Federated Multi-Task Learningcited by 669
  6. 2018Deep learning for time series classification: a reviewcited by 575
  7. 2019Federated Learning with Differential Privacy: Algorithms and Performance Analysiscited by 528
  8. 2018The UCR Time Series Archivecited by 421
  9. 2019Federated Machine Learning: Concept and Applicationscited by 409
  10. 2016Time Series Classification from Scratch with Deep Neural Networks: A Strong Baselinecited by 358
  11. 2020Personalized Cross-Silo Federated Learning on Non-IID Datacited by 282
  12. 2020MINIROCKET: A Very Fast (Almost) Deterministic Transform for Time Series Classificationcited by 186
25 more
  1. 2019SecureBoost: A Lossless Federated Learning Frameworkcited by 174
  2. 2020Benchmarking Multivariate Time Series Classification Algorithmscited by 145
  3. 2021HIVE-COTE 2.0: a new meta ensemble for time series classificationcited by 118
  4. 2020Privacy Preserving Vertical Federated Learning for Tree-based Modelscited by 89
  5. 2021MultiRocket: Multiple pooling operators and transformations for fast and effective time series classificationcited by 89
  6. 2021Federated Learning: Opportunities and Challengescited by 83
  7. 2019Practical Federated Gradient Boosting Decision Treescited by 53
  8. 2019Parallel Distributed Logistic Regression for Vertical Federated Learning without Third-Party Coordinatorcited by 51
  9. 2020The Canonical Interval Forest (CIF) Classifier for Time Series Classificationcited by 48
  10. 2020Omni-Scale CNNs: a simple and effective kernel size configuration for time series classificationcited by 47
  11. 2018A review on distance based time series classificationcited by 40
  12. 2019Practical Differentially Private Top-k Selection with Pay-what-you-get Compositioncited by 38
  13. 2020Throughput-Optimal Topology Design for Cross-Silo Federated Learningcited by 37
  14. 2022BlindFL: Vertical Federated Machine Learning without Peeking into Your Datacited by 36
  15. 2020Large-Scale Secure XGB for Vertical Federated Learningcited by 26
  16. 2021The Temporal Dictionary Ensemble (TDE) Classifier for Time Series Classificationcited by 26
  17. 2019Scalable Dictionary Classifiers for Time Series Classificationcited by 20
  18. 2018Spatio-Temporal Neural Networks for Space-Time Series Forecasting and Relations Discoverycited by 16
  19. 2018From BOP to BOSS and Beyond: Time Series Classification with Dictionary Based Classifierscited by 14
  20. 2021An Efficient Federated Distillation Learning System for Multi-task Time Series Classificationcited by 14
  21. 2020A tale of two toolkits, report the third: on the usage and performance of HIVE-COTE v1.0cited by 12
  22. 2021Privacy-Preserving Feature Selection with Secure Multiparty Computationcited by 12
  23. 2022FedWalk: Communication Efficient Federated Unsupervised Node Embedding with Differential Privacycited by 9
  24. 2021Enabling SQL-based Training Data Debugging for Federated Learningcited by 8
  25. 2019Secure Computation for Machine Learning With SPDZcited by 5

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Decentralized Time Series Classification with ROCKET Featurescited by 0