mlsanityData to 13 Oct 2026

A distillation-based approach integrating continual learning and federated learning for pervasive services

arXiv 2109.04197 ↗First posted 9 Sep 2021cs.AIcited by 42

Not on the map. Why?

Abstract (arXiv)

Federated Learning, a new machine learning paradigm enhancing the use of edge devices, is receiving a lot of attention in the pervasive community to support the development of smart services. Nevertheless, this approach still needs to be adapted to the specificity of the pervasive domain. In particular, issues related to continual learning need to be addressed. In this paper, we present a distillation-based approach dealing with catastrophic forgetting in federated learning scenario. Specifically, Human Activity Recognition tasks are used as a demonstration domain.

Key facts. Cited by 42 papers in the map (data through 13 Oct 2026). Builds on 16 of its 34 references that are in the map. First posted on arXiv 9 Sep 2021.

Builds on

16 of 34 references.

References · 16

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,180
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,653
  3. 2016Overcoming catastrophic forgetting in neural networkscited by 4,753
  4. 2016Learning without Forgettingcited by 2,479
  5. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,323
  6. 2017Memory Aware Synapses: Learning what (not) to forgetcited by 1,099
  7. 2019Towards Federated Learning at Scale: System Designcited by 830
  8. 2019Large Scale Incremental Learningcited by 728
  9. 2018End-to-End Incremental Learningcited by 597
  10. 2020Federated Learning with Matched Averagingcited by 564
  11. 2019Federated Learning with Personalization Layerscited by 539
  12. 2020Class-incremental learning: survey and performance evaluation on image classificationcited by 448
4 more
  1. 2019Federated Learning in Mobile Edge Networks: A Comprehensive Surveycited by 408
  2. 2020Federated Continual Learning with Weighted Inter-client Transfercited by 160
  3. 2020Personalized Federated Learning for Intelligent IoT Applications: A Cloud-Edge based Frameworkcited by 59
  4. 2020Continual Local Training for Better Initialization of Federated Modelscited by 34

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2021: 3; 2022: 6; 2023: 14; 2024: 8; 2025: 8; 2026: 3.

42 papers.

Sort:

By area:

  1. 2023Decentralized Federated Learning: A Survey and Perspectivecited by 86
  2. 2023TARGET: Federated Class-Continual Learning via Exemplar-Free Distillationcited by 65
  3. 2023Better Generative Replay for Continual Federated Learningcited by 53
  4. 2023Federated Continual Learning via Knowledge Fusion: A Surveycited by 53
  5. 2023A Data-Free Approach to Mitigate Catastrophic Forgetting in Federated Class Incremental Learning for Vision Taskscited by 41
  6. 2023Learning Federated Visual Prompt in Null Space for MRI Reconstructioncited by 40
  7. 2021Non-IID data and Continual Learning processes in Federated Learning: A long road aheadcited by 36
  8. 2022MetaFed: Federated Learning among Federations with Cyclic Knowledge Distillation for Personalized Healthcarecited by 36
  9. 2022Graph Lifelong Learning: A Surveycited by 30
  10. 2021Towards Federated Learning on Time-Evolving Heterogeneous Datacited by 23
  11. 2024Text-Enhanced Data-free Approach for Federated Class-Incremental Learningcited by 16
  12. 2024Federated Distillation: A Surveycited by 14
30 more
  1. 2025Federated Continual Learning: Concepts, Challenges, and Solutionscited by 13
  2. 2023Fed-CPrompt: Contrastive Prompt for Rehearsal-Free Federated Continual Learningcited by 12
  3. 2021Ex-Model: Continual Learning from a Stream of Trained Modelscited by 11
  4. 2024Federated Continual Learning for Edge-AI: A Comprehensive Surveycited by 11
  5. 2025Accurate Forgetting for Heterogeneous Federated Continual Learningcited by 11
  6. 2022Continual Horizontal Federated Learning for Heterogeneous Datacited by 8
  7. 2022Speeding up Heterogeneous Federated Learning with Sequentially Trained Superclientscited by 6
  8. 2022Evaluation and comparison of federated learning algorithms for Human Activity Recognition on smartphonescited by 6
  9. 2023Zone-based Federated Learning for Mobile Sensing Datacited by 4
  10. 2023Don't Memorize; Mimic The Past: Federated Class Incremental Learning Without Episodic Memorycited by 4
  11. 2024Overcoming Catastrophic Forgetting in Federated Class-Incremental Learning via Federated Global Twin Generatorcited by 4
  12. 2023Evaluation of Regularization-based Continual Learning Approaches: Application to HARcited by 3
  13. 2023Coordinated Replay Sample Selection for Continual Federated Learningcited by 3
  14. 2024Data-Free Federated Class Incremental Learning with Diffusion-Based Generative Memorycited by 3
  15. 2022Federated Learning and catastrophic forgetting in pervasive computing: demonstration in HAR domaincited by 2
  16. 2023CoDeC: Communication-Efficient Decentralized Continual Learningcited by 2
  17. 2024PIP: Prototypes-Injected Prompt for Federated Class Incremental Learningcited by 2
  18. 2023Masked Autoencoders are Efficient Continual Federated Learnerscited by 1
  19. 2024FedMeS: Personalized Federated Continual Learning Leveraging Local Memorycited by 1
  20. 2025CLAD-Net: Continual Activity Recognition in Multi-Sensor Wearable Systemscited by 1
  21. 2025Decentralized Dynamic Cooperation of Personalized Models for Federated Continual Learningcited by 1
  22. 2026FedSLoP: Memory-Efficient Federated Learning with Low-Rank Gradient Projectioncited by 1
  23. 2023Incremental Semi-supervised Federated Learning for Health Inference via Mobile Sensingcited by 0
  24. 2024Federated Learning with New Knowledge: Fundamentals, Advances, and Futurescited by 0
  25. 2025Asynchronous Federated Continual Segmentation with Evolving Clients and Label Spacescited by 0
  26. 2025TaskVAE: Task-Specific Variational Autoencoders for Exemplar Generation in Continual Learning for Human Activity Recognitioncited by 0
  27. 2025Improving Learning of New Diseases through Knowledge-Enhanced Initialization for Federated Adapter Tuningcited by 0
  28. 2025Dynamic Participation in Federated Learning: Benchmarks and a Knowledge Pool Plugincited by 0
  29. 2026Server-Proximal Aggregation for Federated Domain-Incremental Learning under Partial Participation: Task-Uniform Convergence and Backward Transfercited by 0
  30. 2026PMF-CL: Pareto-Minimal-Forgetting Continual Learner for Conflicting Taskscited by 0