mlsanityData to 7 Oct 2026

An Efficient Federated Distillation Learning System for Multi-task Time Series Classification

arXiv 2201.00011 ↗First posted 30 Dec 2021cs.LG cs.AIcited by 14

Not on the map. Why?

Abstract (arXiv)

This paper proposes an efficient federated distillation learning system (EFDLS) for multi-task time series classification (TSC). EFDLS consists of a central server and multiple mobile users, where different users may run different TSC tasks. EFDLS has two novel components, namely a feature-based student-teacher (FBST) framework and a distance-based weights matching (DBWM) scheme. Within each user, the FBST framework transfers knowledge from its teacher's hidden layers to its student's hidden layers via knowledge distillation, with the teacher and student having identical network structure. For each connected user, its student model's hidden layers' weights are uploaded to the EFDLS server periodically. The DBWM scheme is deployed on the server, with the least square distance used to measure the similarity between the weights of two given models. This scheme finds a partner for each connected user such that the user's and its partner's weights are the closest among all the weights uploaded. The server exchanges and sends back the user's and its partner's weights to these two users which then load the received weights to their teachers' hidden layers. Experimental results show that the proposed EFDLS achieves excellent performance on a set of selected UCR2018 datasets regarding top-1 accuracy.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 28 of its 66 references that are in the map. First posted on arXiv 30 Dec 2021.

Builds on

28 of 66 references.

References · 28

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  3. 2020Knowledge Distillation: A Surveycited by 1,578
  4. 2021Model-Contrastive Federated Learningcited by 762
  5. 2018Deep learning for time series classification: a reviewcited by 575
  6. 2018The UCR Time Series Archivecited by 421
  7. 2019Robust and Communication-Efficient Federated Learning from Non-IID Datacited by 415
  8. 2019Federated Machine Learning: Concept and Applicationscited by 409
  9. 2019InceptionTime: Finding AlexNet for Time Series Classificationcited by 386
  10. 2020Multi-Task Learning with Deep Neural Networks: A Surveycited by 374
  11. 2019A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protectioncited by 371
  12. 2016Time Series Classification from Scratch with Deep Neural Networks: A Strong Baselinecited by 358
16 more
  1. 2021A Comprehensive Survey on Graph Anomaly Detection with Deep Learningcited by 230
  2. 2020MINIROCKET: A Very Fast (Almost) Deterministic Transform for Time Series Classificationcited by 186
  3. 2020Distillation-Based Semi-Supervised Federated Learning for Communication-Efficient Collaborative Training with Non-IID Private Datacited by 125
  4. 2018Multivariate LSTM-FCNs for Time Series Classificationcited by 120
  5. 2019Communication-Efficient Federated Deep Learning with Asynchronous Model Update and Temporally Weighted Aggregationcited by 99
  6. 2013A Time Series Forest for Classification and Feature Extractioncited by 69
  7. 2021Provably Secure Federated Learning against Malicious Clientscited by 60
  8. 2020Federated Knowledge Distillationcited by 51
  9. 2021FLOP: Federated Learning on Medical Datasets using Partial Networkscited by 42
  10. 2021Game of Gradients: Mitigating Irrelevant Clients in Federated Learningcited by 35
  11. 2021PFA: Privacy-preserving Federated Adaptation for Effective Model Personalizationcited by 18
  12. 2018From BOP to BOSS and Beyond: Time Series Classification with Dictionary Based Classifierscited by 14
  13. 2021Learnable Dynamic Temporal Pooling for Time Series Classificationcited by 13
  14. 2020RTFN: A Robust Temporal Feature Network for Time Series Classificationcited by 11
  15. 2020Federated Transfer Learning with Dynamic Gradient Aggregationcited by 8
  16. 2020XEM: An Explainable-by-Design Ensemble Method for Multivariate Time Series Classificationcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 4; 2024: 4; 2025: 2; 2026: 3.

14 papers.

Sort:

  1. 2024Knowledge Distillation in Federated Learning: a Survey on Long Lasting Challenges and New Solutionscited by 8
  2. 2024Improving Local Training in Federated Learning via Temperature Scalingcited by 5
  3. 2024Seamless Detection: Unifying Salient Object Detection and Camouflaged Object Detectioncited by 2
  4. 2026Learning to Reason: Temporal Saliency Distillation for Interpretable Knowledge Transfercited by 2
  5. 2023Feature construction using explanations of individual predictionscited by 1
  6. 2023FedST: Secure Federated Shapelet Transformation for Time Series Classificationcited by 1
  7. 2023An Automated Machine Learning Approach for Detecting Anomalous Peak Patterns in Time Series Data from a Research Watershed in the Northeastern United States Critical Zonecited by 1
  8. 2022Neural Message Passing for Objective-Based Uncertainty Quantification and Optimal Experimental Designcited by 0
  9. 2023Fuzzy Knowledge Distillation from High-Order TSK to Low-Order TSKcited by 0
  10. 2024A Hybrid Federated Kernel Regularized Least Squares Algorithmcited by 0
  11. 2025ColNet: Collaborative Optimization in Decentralized Federated Multi-task Learning Systemscited by 0
  12. 2025Provably Near-Optimal Federated Ensemble Distillation with Negligible Overheadcited by 0
2 more
  1. 2026MemKD: Memory-Discrepancy Knowledge Distillation for Efficient Time Series Classificationcited by 0
  2. 2026Probabilistic Federated Learning on Uncertain and Heterogeneous Data with Model Personalizationcited by 0