mlsanityData to 7 Oct 2026

Concept drift detection and adaptation for federated and continual learning

arXiv 2105.13309 ↗First posted 27 May 2021cs.LGcited by 32

Not on the map. Why?

Abstract (arXiv)

Smart devices, such as smartphones, wearables, robots, and others, can collect vast amounts of data from their environment. This data is suitable for training machine learning models, which can significantly improve their behavior, and therefore, the user experience. Federated learning is a young and popular framework that allows multiple distributed devices to train deep learning models collaboratively while preserving data privacy. Nevertheless, this approach may not be optimal for scenarios where data distribution is non-identical among the participants or changes over time, causing what is known as concept drift. Little research has yet been done in this field, but this kind of situation is quite frequent in real life and poses new challenges to both continual and federated learning. Therefore, in this work, we present a new method, called Concept-Drift-Aware Federated Averaging (CDA-FedAvg). Our proposal is an extension of the most popular federated algorithm, Federated Averaging (FedAvg), enhancing it for continual adaptation under concept drift. We empirically demonstrate the weaknesses of regular FedAvg and prove that CDA-FedAvg outperforms it in this type of scenario.

Key facts. Cited by 32 papers in the map (data through 7 Oct 2026). Builds on 16 of its 33 references that are in the map. First posted on arXiv 27 May 2021.

Builds on

16 of 33 references.

References · 16

  1. 2019Advances and Open Problems in Federated Learningcited by 3,021
  2. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  3. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,531
  4. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,461
  5. 2018Continual Lifelong Learning with Neural Networks: A Reviewcited by 1,313
  6. 2018Federated Learning with Non-IID Datacited by 1,099
  7. 2018LEAF: A Benchmark for Federated Settingscited by 780
  8. 2019Three scenarios for continual learningcited by 610
  9. 2018Federated Learning for Mobile Keyboard Predictioncited by 565
  10. 2020Learning under Concept Drift: A Reviewcited by 470
  11. 2020Adaptive Personalized Federated Learningcited by 353
  12. 2015Federated Optimization:Distributed Optimization Beyond the Datacentercited by 193
4 more
  1. 2020Federated Continual Learning with Weighted Inter-client Transfercited by 158
  2. 2015Characterizing Concept Driftcited by 93
  3. 2019Continual Learning for Robotics: Definition, Framework, Learning Strategies, Opportunities and Challengescited by 92
  4. 2020Federated and continual learning for classification tasks in a society of devicescited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 4; 2023: 10; 2024: 6; 2025: 4; 2026: 3.

32 papers.

Sort:

By area:

  1. 2023TARGET: Federated Class-Continual Learning via Exemplar-Free Distillationcited by 64
  2. 2021Non-IID data and Continual Learning processes in Federated Learning: A long road aheadcited by 36
  3. 2022Federated Learning under Distributed Concept Driftcited by 35
  4. 2021Towards Federated Learning on Time-Evolving Heterogeneous Datacited by 23
  5. 2023Performative Federated Learning: A Solution to Model-Dependent and Heterogeneous Distribution Shiftscited by 14
  6. 2021FUTURE-AI: Guiding Principles and Consensus Recommendations for Trustworthy Artificial Intelligence in Medical Imagingcited by 13
  7. 2023Fed-CPrompt: Contrastive Prompt for Rehearsal-Free Federated Continual Learningcited by 12
  8. 2021Tackling Dynamics in Federated Incremental Learning with Variational Embedding Rehearsalcited by 11
  9. 2022Online Federated Learning via Non-Stationary Detection and Adaptation amidst Concept Driftcited by 9
  10. 2023On the Local Cache Update Rules in Streaming Federated Learningcited by 8
  11. 2024Classifier Clustering and Feature Alignment for Federated Learning under Distributed Concept Driftcited by 8
  12. 2022Federated Continual Learning for Socially Aware Roboticscited by 5
20 more
  1. 2023Jointly Exploring Client Drift and Catastrophic Forgetting in Dynamic Learningcited by 5
  2. 2022Federated Continual Learning to Detect Accounting Anomalies in Financial Auditingcited by 4
  3. 2023A Survey of Incremental Transfer Learning: Combining Peer-to-Peer Federated Learning and Domain Incremental Learning for Multicenter Collaborationcited by 4
  4. 2021Attentive Federated Learning for Concept Drift in Distributed 5G Edge Networkscited by 3
  5. 2023On Knowledge Editing in Federated Learning: Perspectives, Challenges, and Future Directionscited by 3
  6. 2024Federated Learning Clients Clustering with Adaptation to Data Driftscited by 3
  7. 2023Machine Learning for QoS Prediction in Vehicular Communication: Challenges and Solution Approachescited by 2
  8. 2024Unveiling Group-Specific Distributed Concept Drift: A Fairness Imperative in Federated Learningcited by 2
  9. 2024FLAME: Adaptive and Reactive Concept Drift Mitigation for Federated Learning Deploymentscited by 2
  10. 2023Concept Matching: Clustering-based Federated Continual Learningcited by 1
  11. 2024A Comprehensive Review of Machine Learning Advances on Data Change: A Cross-Field Perspectivecited by 1
  12. 2025FedDAA: Dynamic Client Clustering for Concept Drift Adaptation in Federated Learningcited by 1
  13. 2025Holistic Continual Learning under Concept Drift with Adaptive Memory Realignmentcited by 1
  14. 2026Federated continual learning: A comprehensive survey on lifelong and privacy-preserving learning over distributed and non-stationary datacited by 1
  15. 2026C2FL: Clustered Continual Federated Learning under Spatial and Temporal Driftcited by 1
  16. 2023AI Models Close to your Chest: Robust Federated Learning Strategies for Multi-site CTcited by 0
  17. 2024Towards Privacy-Aware and Personalised Assistive Robots: A User-Centred Approachcited by 0
  18. 2025Dynamic Allocation Hypernetwork with Adaptive Model Recalibration for FCLcited by 0
  19. 2025Shift Happens: Mixture of Experts based Continual Adaptation in Federated Learningcited by 0
  20. 2026Federated Learning Under Temporal Drift -- Mitigating Catastrophic Forgetting via Experience Replaycited by 0