pith. sign in

arxiv: 2606.11272 · v1 · pith:GSXNZXRHnew · submitted 2026-06-09 · 💻 cs.LG · cs.AI

Federated continual learning: A comprehensive survey on lifelong and privacy-preserving learning over distributed and non-stationary data

Masoume Gholizade , Fabrizio Ruffini , Pietro Ducange , Francesco Marcelloni This is my paper

Pith reviewed 2026-06-27 14:18 UTC · model grok-4.3

classification 💻 cs.LG cs.AI
keywords federated learningcontinual learninglifelong learningprivacy preservationnon-stationary datadistributed learningcatastrophic forgettingsurvey
0
0 comments X

The pith

Federated continual learning supports lifelong adaptation in privacy-preserving distributed systems facing non-stationary data.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper defines federated continual learning as the necessary intersection of federated learning and continual learning to enable lifelong, adaptive, privacy-aware training over distributed clients whose data distributions change over time. It shows that classical federated learning implicitly assumes stationary data and therefore degrades with instability and catastrophic forgetting in settings such as healthcare and industrial IoT. The survey supplies a formal problem statement, a multi-dimensional taxonomy of existing methods, reviews of application domains and evaluation metrics, and a list of open challenges including extreme heterogeneity under temporal drift. A sympathetic reader would care because deployable real-world federated systems require mechanisms that continue to learn without violating privacy or communication limits once data begins to drift.

Core claim

Federated Continual Learning emerges at the intersection of federated learning and continual learning to support lifelong, adaptive, and privacy-aware learning over distributed and non-stationary data; the survey formalizes the problem, analyzes the breakdown of classical federated methods under non-stationarity, proposes a multi-dimensional taxonomy, summarizes representative applications and metrics, and identifies open challenges such as scalable privacy-preserving memory and standardized long-term benchmarks.

What carries the argument

The multi-dimensional taxonomy of FCL approaches that organizes methods for integrating continual-learning principles into federated systems to counteract performance degradation and forgetting.

If this is right

  • Classical federated learning will exhibit instability and catastrophic forgetting once data distributions drift across clients or over time.
  • Continual learning techniques must be adapted to respect federated constraints on communication, privacy, and client heterogeneity.
  • Evaluation protocols must track long-term performance and forgetting rather than single-round accuracy.
  • Standardized benchmarks and privacy-preserving memory mechanisms become necessary for progress toward deployable systems.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • FCL methods could be tested on controlled temporal-drift benchmarks that isolate the effects of client heterogeneity from distribution shift.
  • Connections to edge-computing constraints in smart-city or cybersecurity settings may impose additional limits on memory size and update frequency.
  • Hybrid designs that combine FCL with other adaptation strategies could address cases of extreme non-stationarity not yet covered by current taxonomies.

Load-bearing premise

Classical federated learning methods assume that data distributions remain stationary across clients and over time.

What would settle it

An experiment in which standard federated learning algorithms exhibit no measurable performance degradation or forgetting when trained on non-stationary data streams from heterogeneous clients would falsify the central premise.

Figures

Figures reproduced from arXiv: 2606.11272 by Fabrizio Ruffini, Francesco Marcelloni, Masoume Gholizade, Pietro Ducange.

Figure 1
Figure 1. Figure 1: Overall structure of the paper. 5 [PITH_FULL_IMAGE:figures/full_fig_p005_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Comparison between FL with stationary datasets (left) and FCL with time [PITH_FULL_IMAGE:figures/full_fig_p011_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: PRISMA flow diagram of the literature selection process. [PITH_FULL_IMAGE:figures/full_fig_p012_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Temporal distribution of the initial search results retrieved from Scopus and [PITH_FULL_IMAGE:figures/full_fig_p014_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Overall taxonomy of FCL approaches. ulate the stability–plasticity trade-off and mitigate forgetting at the client level. Aggregation and Communication schemes address system heterogene￾ity, limited bandwidth, and intermittent participation, often incorporating asynchronous or staleness-aware updates. Personalization mechanisms han￾dle persistent statistical heterogeneity by isolating client-specific compo… view at source ↗
Figure 7
Figure 7. Figure 7: A conceptual view of FCL across application domains: healthcare, IIoT, smart [PITH_FULL_IMAGE:figures/full_fig_p043_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: Donut chart summarizing dataset realism (inner ring) and modality categories [PITH_FULL_IMAGE:figures/full_fig_p054_8.png] view at source ↗
read the original abstract

Federated Learning (FL) enables collaborative and privacy-preserving model training across distributed clients, but most existing FL systems implicitly assume data stationarity. In real-world settings-such as healthcare, industrial IoT (IIOT), cybersecurity, and smart cities-data streams are inherently non-stationary, leading classical FL methods to suffer from performance degradation, instability, and catastrophic forgetting. Continual Learning (CL) addresses learning under evolving data distributions but has been largely studied in centralized settings, overlooking key constraints of federated systems, including privacy, limited communication, and client heterogeneity. Federated Continual Learning (FCL) emerges at the intersection of FL and CL, aiming to support lifelong, adaptive, and privacy-aware learning over distributed and non-stationary data. This survey provides a comprehensive and systematic overview of FCL. We first present a formal definition of the FCL problem and clarify its distinctive characteristics. We then analyze the limitations of classical FL under non-stationary conditions, highlighting how CL principles support long-term adaptation. To organize the rapidly growing literature, we propose a multi-dimensional taxonomy of FCL approaches. Furthermore, we review representative application domains and data modalities, summarize commonly used evaluation metrics, and discuss experimental perspectives for assessing long-term performance and forgetting. Finally, we highlight key open challenges, including handling extreme heterogeneity under temporal drift, designing scalable and privacy-preserving memory mechanisms, and establishing standardized benchmarks. This survey aims to serve as a reference and a roadmap for advancing FCL toward robust and deployable real-world systems.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

0 major / 2 minor

Summary. The paper is a survey on Federated Continual Learning (FCL). It formally defines the FCL problem, analyzes how classical FL methods degrade under non-stationary data distributions due to catastrophic forgetting and instability, proposes a multi-dimensional taxonomy to classify existing FCL approaches, reviews representative application domains (healthcare, IIoT, cybersecurity) and data modalities, summarizes evaluation metrics and experimental practices for long-term performance, and identifies open challenges such as extreme heterogeneity under temporal drift and scalable privacy-preserving memory mechanisms.

Significance. If the taxonomy is comprehensive and the synthesis accurate, the survey would provide a valuable organizing framework and roadmap for research at the intersection of federated and continual learning. It explicitly credits the formal problem definition, the multi-dimensional taxonomy, and the structured review of metrics and benchmarks as contributions that can help standardize evaluation of lifelong adaptation in distributed, privacy-constrained settings.

minor comments (2)
  1. [Abstract] The abstract and introduction use both 'IIOT' and 'IIoT'; standardize the acronym for consistency across the manuscript.
  2. [Taxonomy] The taxonomy section would benefit from an explicit justification or decision tree explaining how the chosen dimensions (e.g., memory mechanisms, heterogeneity handling) were selected over alternatives in the literature.

Simulated Author's Rebuttal

0 responses · 0 unresolved

We thank the referee for their constructive summary of our survey and for recommending minor revision. No specific major comments were raised in the report.

Circularity Check

0 steps flagged

No significant circularity; survey paper with no derivations

full rationale

This is a survey paper whose contribution consists of a formal definition of FCL, a multi-dimensional taxonomy, literature synthesis, and discussion of open challenges. No equations, predictions, fitted parameters, or theoretical derivations are present that could reduce to inputs by construction. The central claims rest on external prior work reviewed in the survey rather than any self-referential chain internal to the paper. This matches the default expectation for non-derivational survey work and receives the lowest circularity score.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

This is a survey paper; it introduces no new mathematical models, parameters, axioms, or entities.

pith-pipeline@v0.9.1-grok · 5819 in / 1098 out tokens · 31328 ms · 2026-06-27T14:18:05.842515+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

97 extracted references · 85 canonical work pages · 1 internal anchor

  1. [2]

    J. L. Corcuera Bárcena, M. Daole, P. Ducange, F. Marcelloni, A. Renda, F. Ruffini, A. Schiavo, Fed-xai: Federated learning of explainable arti- ficial intelligence models, in: Proceedings of the 3rd Italian Workshop on Explainable Artificial Intelligence (XAI.it 2022), Vol. 3277 of CEUR Workshop Proceedings, 2022. URLhttp://ceur-ws.org/Vol-3277/

    2022

  2. [3]

    Kalakoti, S

    R. Kalakoti, S. Nõmm, H. Bahsi, Federated learning of explainable ai(fedxai) for deep learning-based intrusion detection in iot networks, Computer Networks 270 (2025) 111479.doi:https://doi.org/10.1 016/j.comnet.2025.111479

    arXiv 2025

  3. [4]

    Cossu, A

    A. Cossu, A. Carta, L. Passaro, V. Lomonaco, T. Tuytelaars, D. Bac- ciu, Continual pre-training mitigates forgetting in language and vision, Neural Networks 179 (2024) 106492.doi:https://doi.org/10.1016/ j.neunet.2024.106492

    arXiv 2024

  4. [5]

    S. Li, T. Su, X.-Y. Zhang, Z. Wang, Continual learning with knowl- edge distillation: A survey, IEEE Transactions on Neural Networks and Learning Systems (2025).doi:10.1109/TNNLS.2024.3476068. 65

    work page doi:10.1109/tnnls.2024.3476068 2025

  5. [6]

    L. Chen, D. Zhao, Y. Gao, J. Zhou, T. C. Wei, Fedmtl: Adaptive multi-teacher knowledge distillation for federated continual learning, Knowledge-Based Systems (2025) 115160

    2025

  6. [7]

    Zhang, Y

    Z. Zhang, Y. Zhang, H. Li, S. Liu, W. Chen, Z. Zhang, L. Tang, Federated continual representation learning for evolutionary distributed intrusion detection in industrial internet of things, Engineering Ap- plications of Artificial Intelligence 135 (2024) 108826.doi:https: //doi.org/10.1016/j.engappai.2024.108826

    work page doi:10.1016/j.engappai.2024.108826 2024

  7. [8]

    L. Wang, X. Zhang, H. Su, J. Zhu, A comprehensive survey of con- tinual learning: Theory, method and application, IEEE Transactions on Pattern Analysis and Machine Intelligence 46 (8) (2024) 5362–5383. doi:10.1109/TPAMI.2024.3367329

    work page doi:10.1109/tpami.2024.3367329 2024

  8. [9]

    M. F. Criado, F. E. Casado, R. Iglesias, C. V. Regueiro, S. Barro, Non- iid data and continual learning processes in federated learning: A long road ahead, Information Fusion 88 (2022) 263–280.doi:10.1016/j.in ffus.2022.07.024

    work page doi:10.1016/j.in 2022

  9. [10]

    X. Yang, H. Yu, X. Gao, H. Wang, J. Zhang, T. Li, Federated con- tinual learning via knowledge fusion: A survey, IEEE Transactions on Knowledge and Data Engineering 36 (8) (2024) 3832–3850.doi: 10.1109/TKDE.2024.3363240

    work page doi:10.1109/tkde.2024.3363240 2024

  10. [11]

    Z. Wang, F. Wu, F. Yu, Y. Zhou, J. Hu, G. Min, Federated con- tinual learning for edge-ai: A comprehensive survey., arXiv preprint arXiv:2411.13740 (2024)

    arXiv 2024

  11. [12]

    Hamedi, R

    P. Hamedi, R. Razavi-Far, E. Hallaji, Federated continual learning: Concepts, challenges, andsolutions, Neurocomputing651(2025)130844. doi:https://doi.org/10.1016/j.neucom.2025.130844

    work page doi:10.1016/j.neucom.2025.130844 2025

  12. [13]

    Birashk, L

    A. Birashk, L. Khan, Federated continual learning for task-incremental and class-incremental problems: A survey, Expert Systems with Appli- cations 297 (2026) 129278.doi:https://doi.org/10.1016/j.eswa.2 025.129278

    work page doi:10.1016/j.eswa.2 2026

  13. [14]

    Savoia, D

    M. Savoia, D. Annunziata, D. Thakur, G. Fortino, F. Piccialli, Fed- erated continual learning meets digital twins: A survey on methods, 66 intersections and perspectives, Neurocomputing 681 (2026) 133366. doi:https://doi.org/10.1016/j.neucom.2026.133366

    work page doi:10.1016/j.neucom.2026.133366 2026

  14. [15]

    M. Ye, X. Fang, B. Du, P. C. Yuen, D. Tao, Heterogeneous federated learning: State-of-the-artandresearchchallenges, ACMComputingSur- veys (2023).doi:10.1145/3625558

    work page doi:10.1145/3625558 2023

  15. [16]

    A.Nandi, F.Xhafa, R.Kumar, Adocker-basedfederatedlearningframe- work design and deployment for multi-modal data stream classification, Computing 105 (2023) 2195–2229.doi:10.1007/s00607-023-01179-5

    work page doi:10.1007/s00607-023-01179-5 2023

  16. [17]

    Nandi, F

    A. Nandi, F. Xhafa, A federated learning method for real-time emotion state classification from multi-modal streaming, Methods 204 (2022) 340–347.doi:https://doi.org/10.1016/j.ymeth.2022.03.005

    work page doi:10.1016/j.ymeth.2022.03.005 2022

  17. [18]

    J. Cai, X. Liu, Q. Ye, Y. Liu, Y. Wang, A federated learning framework based on differentially private continuous data release, IEEE Transac- tions on Dependable and Secure Computing 21 (5) (2024) 4879–4894. doi:10.1109/TDSC.2024.3364060

    work page doi:10.1109/tdsc.2024.3364060 2024

  18. [19]

    J. L. Corcuera Bárcena, P. Ducange, A. Ercolani, F. Marcelloni, A. Renda, An approach to federated learning of explainable fuzzy regres- sion models, in: 2022 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), IEEE, 2022.doi:10.1109/FUZZ-IEEE55066.2022.98 82881

    work page doi:10.1109/fuzz-ieee55066.2022.98 2022

  19. [20]

    A.Yazdinejad, Z.DehghaniMohammadabadi, A.Dehghantanha, G.Sri- vastava, An explainable and privacy-preserving federated learning model for threat detection in cyber-physical-social systems, IEEE Transactions on Computational Social Systems (2025).doi:10.1109/TCSS.2025.36 06798

    work page doi:10.1109/tcss.2025.36 2025

  20. [21]

    Y. Wu, H. Yang, X. Wang, H. Yu, A. El Saddik, M. S. Hossain, An effective federated learning system for industrial iot data stream- ing, Alexandria Engineering Journal 105 (2024) 414–422.doi:https: //doi.org/10.1016/j.aej.2024.07.040

    work page doi:10.1016/j.aej.2024.07.040 2024

  21. [22]

    Y. Jin, L. Jiao, Z. Qian, S. Zhang, S. Lu, Budget-aware online control of edge federated learning on streaming data with stochastic inputs, IEEE Journal on Selected Areas in Communications 39 (12) (2021) 3704–3722. doi:10.1109/JSAC.2021.3118421. 67

    work page doi:10.1109/jsac.2021.3118421 2021

  22. [23]

    Zhang, Y

    Z. Zhang, Y. Zhang, D. Guo, C. Lin, J. Wang, X. Yang, Communication- efficientfederatedcontinuallearningfordistributedlearningsystemwith non-iid data, Science China Information Sciences 66 (12) (2023) 122102. doi:10.1007/s11432-020-3419-4

    work page doi:10.1007/s11432-020-3419-4 2023

  23. [24]

    T. Zhou, B. Wang, Cross paradigm fusion of federated and contin- ual learning on multilayer perceptron mixer architecture for incremen- tal thoracic infection diagnosis, Scientific Reports 15 (24449) (2025). doi:10.1038/s41598-025-06077-8

    work page doi:10.1038/s41598-025-06077-8 2025

  24. [25]

    Zhang, B

    Z. Zhang, B. Guo, W. Sun, Y. Liu, Z. Yu, Cross-fcl: Toward a cross- edge federated continual learning framework in mobile edge computing systems, IEEE Transactions on Mobile Computing 23 (1) (2024) 313– 326.doi:10.1109/TMC.2022.3223944

    work page doi:10.1109/tmc.2022.3223944 2024

  25. [26]

    F.Shan, Y.Liu, L.Fan, Y.Mao, Z.Chen, S.Li, Asurveyofoptimization algorithms for differential privacy in federated learning, Journal of Sys- tems Architecture (2025) 103582doi:10.1016/j.sysarc.2025.103582

    work page doi:10.1016/j.sysarc.2025.103582 2025

  26. [27]

    W. Liu, X. Zhang, J. Duan, C. Joe-Wong, Z. Zhou, X. Chen, Dy- namite: Dynamic interplay of mini-batch size and aggregation fre- quency for federated learning with static and streaming datasets, IEEE Transactions on Mobile Computing 23 (7) (2024) 7664–7679.doi: 10.1109/TMC.2023.3337016

    work page doi:10.1109/tmc.2023.3337016 2024

  27. [28]

    Understanding and

    M. De Lange, T. Tuytelaars, Continual prototype evolution: Learning online from non-stationary data streams, in: 2021 IEEE/CVF Interna- tional Conference on Computer Vision (ICCV), 2021, pp. 8230–8239. doi:10.1109/ICCV48922.2021.00814

    work page doi:10.1109/iccv48922.2021.00814 2021

  28. [29]

    H. Shi, Z. Xu, H. Wang, W. Qin, W. Wang, Y. Wang, Z. Wang, S. Ebrahimi, H. Wang, Continual learning of large language mod- els: A comprehensive survey, ACM Computing Surveys 58 (5) (2025). doi:10.1145/3735633

    work page doi:10.1145/3735633 2025

  29. [30]

    iCaRL: Incremental Classifier and Representation Learning

    S.-A.Rebuffi, A.Kolesnikov, G.Sperl, C.H.Lampert, icarl: Incremental classifier and representation learning, in: Proceedings of the IEEE con- ference on Computer Vision and Pattern Recognition, 2017, pp. 2001– 2010.doi:10.48550/arXiv.1611.07725. 68

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.1611.07725 2017

  30. [31]

    Rolnick, A

    D. Rolnick, A. Ahuja, J. Schwarz, T. Lillicrap, G. Wayne, Experience replay for continual learning, in: H. Wallach, H. Larochelle, A. Beygelz- imer, F. d'Alché-Buc, E. Fox, R. Garnett (Eds.), Advances in Neural Information Processing Systems, Vol. 32, Curran Associates, Inc., 2019. URLhttps://proceedings.neurips.cc/paper_files/paper/2019/ file/fa7cdfad1a5...

    2019

  31. [32]

    Z.Li, D.Hoiem, Learningwithoutforgetting, IEEETrans.PatternAnal. Mach. Intell. 40 (12) (2018) 2935–2947.doi:10.1109/TPAMI.2017.277 3081

    work page doi:10.1109/tpami.2017.277 2018

  32. [33]

    Krishnan, P

    R. Krishnan, P. Rajpurkar, E. J. Topol, Self-supervised learning in medicine and healthcare, Nature Biomedical Engineering 6 (12) (2022) 1346–1352.doi:10.1038/s41551-022-00914-1

    work page doi:10.1038/s41551-022-00914-1 2022

  33. [34]

    Iqbal, X

    S. Iqbal, X. Zhong, M. A. Khan, Z. Wu, D. A. AlHammadi, W. Liu, I. A. Choudhry, Continual and wisdom learning for federated learning: A comprehensive framework for robustness and debiasing, Information Processing & Management 62 (5) (2025) 104157.doi:https://doi.or g/10.1016/j.ipm.2025.104157

    work page doi:10.1016/j.ipm.2025.104157 2025

  34. [35]

    Z. Yang, S. Zhang, C. Li, M. Wang, H. Wang, M. Zhang, Efficient knowledge management for heterogeneous federated continual learning on resource-constrained edge devices, Future Generation Computer Sys- tems 156 (2024) 16–29.doi:https://doi.org/10.1016/j.future.2 024.02.018

    work page doi:10.1016/j.future.2 2024

  35. [36]

    Zhang, X

    W. Zhang, X. Wang, P. Zhou, W. Wu, X. Zhang, Client selection for federated learning with non-iid data in mobile edge computing, IEEE Access 9 (2021) 24462–24474.doi:10.1109/ACCESS.2021.3056919

    work page doi:10.1109/access.2021.3056919 2021

  36. [37]

    Z. Zhao, F. Lyu, L. Li, F. Hu, M. Gu, L. Sun, Towards long-term remem- bering in federated continual learning, Cognitive Computation 16 (7) (2024) 2803–2811.doi:10.1007/s12559-024-10314-z

    work page doi:10.1007/s12559-024-10314-z 2024

  37. [38]

    H. Sun, W. Zhang, R. Zhang, L. Xu, H. Guan, H. Zhao, B. Zhang, S. Yang, X. Yu, Federated continual learning based on weakly supervised diffusion models for disease diagnosis, IEEE Internet of Things Journal 12 (22) (2025) 45958–45971.doi:10.1109/JIOT.2025.3535628. 69

    work page doi:10.1109/jiot.2025.3535628 2025

  38. [39]

    M. J. Page, J. E. McKenzie, P. M. Bossuyt, I. Boutron, T. C. Hoff- mann, C. D. Mulrow, L. Shamseer, J. M. Tetzlaff, D. Moher, Updating guidance for reporting systematic reviews: development of the prisma 2020 statement, Journal of Clinical Epidemiology 134 (2021) 103–112. doi:https://doi.org/10.1016/j.jclinepi.2021.02.003. URLhttps://www.sciencedirect.com...

    work page doi:10.1016/j.jclinepi.2021.02.003 2020

  39. [40]

    J. Le, X. Lei, N. Mu, H. Zhang, K. Zeng, X. Liao, Federated continuous learning with broad network architecture, IEEE Transactions on Cyber- netics 51 (8) (2021) 3874–3888.doi:10.1109/TCYB.2021.3090260

    work page doi:10.1109/tcyb.2021.3090260 2021

  40. [41]

    F. E. Casado, D. Lema, R. Iglesias, et al., Ensemble and continual fed- erated learning for classification tasks, Machine Learning 112 (9) (2023) 3413–3453.doi:10.1007/s10994-023-06330-z

    work page doi:10.1007/s10994-023-06330-z 2023

  41. [42]

    C. B. Mawuli, L. Che, J. Kumar, S. U. Din, Z. Qin, Q. Yang, J. Shao, Fedstream: Prototype-based federated learning on distributed concept- drifting data streams, IEEE Transactions on Systems, Man, and Cyber- netics: Systems 53 (11) (2023) 7112–7124.doi:10.1109/TSMC.2023. 3293462

    work page doi:10.1109/tsmc.2023 2023

  42. [43]

    C. B. Mawuli, J. Kumar, E. Nanor, S. Fu, L. Pan, Q. Yang, W. Zhang, J. Shao, Semi-supervised federated learning on evolving data streams, Information Sciences 643 (2023) 119235.doi:https://doi.org/10.1 016/j.ins.2023.119235

    arXiv 2023

  43. [44]

    L. Yu, L. Ge, G. Wang, J. Yin, Q. Chen, J. Zhou, L. He, Pi-fed: Continual federated learning with parameter-level importance aggre- gation, IEEE Internet of Things Journal 11 (22) (2024) 37187–37199. doi:10.1109/JIOT.2024.3440029

    work page doi:10.1109/jiot.2024.3440029 2024

  44. [45]

    Z.Wang, Y.Zhang, X.Xu, Z.Fu, H.Yang, W.Du, Federatedprobability memory recall for federated continual learning, Information Sciences 629 (2023) 551–565.doi:https://doi.org/10.1016/j.ins.2023.02.015

    work page doi:10.1016/j.ins.2023.02.015 2023

  45. [46]

    H. Wang, J. Bian, J. Xu, On the local cache update rules in streaming federatedlearning, IEEEInternetofThingsJournal11(6)(2024)10808– 10816.doi:10.1109/JIOT.2023.3327316. 70

    work page doi:10.1109/jiot.2023.3327316 2024

  46. [47]

    N. Wang, X. Li, Z. Guan, S. Yuan, Fedstream: A federated learning framework on heterogeneous streaming data for next-generation traffic analysis, IEEE Transactions on Network Science and Engineering 11 (3) (2024) 2485–2496.doi:10.1109/TNSE.2023.3292805

    work page doi:10.1109/tnse.2023.3292805 2024

  47. [48]

    Baccarelli, M

    E. Baccarelli, M. Scarpiniti, A. Momenzadeh, S. Sarv Ahrabi, Afafed—asynchronous fair adaptive federated learning for iot stream ap- plications, Computer Communications 195 (2022) 376–402.doi:https: //doi.org/10.1016/j.comcom.2022.09.016

    work page doi:10.1016/j.comcom.2022.09.016 2022

  48. [49]

    S. Zeng, Z. Li, H. Yu, Z. Zhang, L. Luo, B. Li, D. Niyato, Hfedms: Het- erogeneous federated learning with memorable data semantics in indus- trial metaverse, IEEE Transactions on Cloud Computing 11 (3) (2023) 3055–3069.doi:10.1109/TCC.2023.3254587

    work page doi:10.1109/tcc.2023.3254587 2023

  49. [50]

    SAITS: Self-attention-based imputation for time se- ries.Expert Systems with Applications, 219:119619, 2023

    T. Xiong, C. Zhang, M. Rong, D. Gong, S. Yang, Adaptivestreamfl: A bayesian-enhancedmulti-scalefederatedlearningframeworkfordynamic data streams with uncertainty quantification, Expert Systems with Ap- plications 299 (2026) 129882.doi:https://doi.org/10.1016/j.eswa .2025.129882

    work page doi:10.1016/j.eswa 2026

  50. [51]

    B. Li, P. Song, C. Zhao, M. Xie, Facing spatiotemporal heterogeneity: A unified federated continual learning framework with self-challenge re- hearsal for industrial monitoring tasks, Knowledge-Based Systems 289 (2024) 111491.doi:https://doi.org/10.1016/j.knosys.2024.1114 91

    work page doi:10.1016/j.knosys.2024.1114 2024

  51. [52]

    K.O.Lamptey, B.J.Ayekai, S.UdDin, Federatedlearningonmultilabel evolving data streams, IEEE Internet of Things Journal 12 (20) (2025) 42103–42115.doi:10.1109/JIOT.2025.3592954

    work page doi:10.1109/jiot.2025.3592954 2025

  52. [53]

    doi: 10.1016/j.neucom

    S. Iqbal, M. A. Khan, G. Mustafa, S. Ayouni, A. Aljohani, A. Hussain, Fedcapd: Federated class-incremental learning via capsule distillation and diffusion replay, Neurocomputing (2026).doi:10.1016/j.neucom .2026.133365

    work page doi:10.1016/j.neucom 2026

  53. [54]

    L. Chen, D. Zhao, Y. Gao, J. Zhou, C. W. Tan, Fedmtl: Adaptive multi-teacher knowledge distillation for federated continual learning, Knowledge-Based Systems (2026).doi:10.1016/j.knosys.2025. 115160. 71

    work page doi:10.1016/j.knosys.2025 2026

  54. [55]

    Y. Liu, F. Liu, B. Guo, Z. Zhang, R. Xu, Z. Yu, Sparse-fcl: Sparse federated continual learning for evolving mobile edge computing en- vironments, IEEE Transactions on Services Computing 18 (4) (2025) 2403–2416.doi:10.1109/TSC.2025.3583174

    work page doi:10.1109/tsc.2025.3583174 2025

  55. [56]

    J. Chen, J. He, J. Tang, W. Li, Z. Yin, Knowledge efficient federated continual learning for industrial edge systems, IEEE Transactions on Network Science and Engineering 12 (3) (2025) 2107–2120.doi:10.1 109/TNSE.2025.3544614

    arXiv 2025

  56. [57]

    D. Li, N. Huang, Z. Wang, H. Yang, Personalized federated continual learning for task-incremental biometrics, IEEE Internet of Things Jour- nal 10 (23) (2023) 20776–20788.doi:10.1109/JIOT.2023.3284843

    work page doi:10.1109/jiot.2023.3284843 2023

  57. [58]

    L. Sun, J. Wu, Y. Xu, Y. Zhang, A federated learning and blockchain frameworkforphysiologicalsignalclassificationbasedoncontinuallearn- ing, Information Sciences 630 (2023) 586–598.doi:https://doi.org/ 10.1016/j.ins.2023.02.003

    work page doi:10.1016/j.ins.2023.02.003 2023

  58. [59]

    A. J. Chaves, C. Martín, M. Díaz, Towards flexible data stream collab- oration: Federated learning in kafka-ml, Internet of Things 25 (2024) 101036.doi:https://doi.org/10.1016/j.iot.2023.101036

    work page doi:10.1016/j.iot.2023.101036 2024

  59. [60]

    H. Li, Z. Wang, N. Zeng, P. Wu, Y. Li, Promoting objective knowledge transfer: A cascaded fuzzy system for solving dynamic multiobjective optimization problems, IEEE Transactions on Fuzzy Systems 32 (11) (2024) 6199–6213.doi:10.1109/TFUZZ.2024.3443207

    work page doi:10.1109/tfuzz.2024.3443207 2024

  60. [61]

    J. Cai, Q. Ye, H. Hu, X. Liu, Y. Fu, Boosting accuracy of differentially private continuous data release for federated learning, IEEE Transac- tions on Information Forensics and Security 19 (2024) 10287–10301. doi:10.1109/TIFS.2024.3477325

    work page doi:10.1109/tifs.2024.3477325 2024

  61. [62]

    J. Hu, H. Zhang, Fgs-fl: Enhancing federated learning with differential privacy via flat gradient stream, Expert Systems with Applications 288 (2025) 128273.doi:https://doi.org/10.1016/j.eswa.2025.128273

    work page doi:10.1016/j.eswa.2025.128273 2025

  62. [63]

    H. Li, Z. Fang, L. Hu, H. Liu, P. Wu, N. Zeng, A novel popula- tion robustness-based switching response framework for solving dy- namic multi-objective problems, Neurocomputing 583 (2024) 127601. doi:https://doi.org/10.1016/j.neucom.2024.127601. 72

    work page doi:10.1016/j.neucom.2024.127601 2024

  63. [64]

    K. Zhu, W. Chen, L. Jiao, J. Wang, Y. Peng, L. Zhang, Online training data acquisition for federated learning in cloud-edge networks, Com- puter Networks (2023).doi:10.1016/j.comnet.2023.109556

    work page doi:10.1016/j.comnet.2023.109556 2023

  64. [65]

    D. Su, Y. Zhou, L. Cui, Q. Z. Sheng, Communication cost-aware client selection in online federated learning: A lyapunov approach, Computer Networks (2024).doi:10.1016/j.comnet.2024.110517

    work page doi:10.1016/j.comnet.2024.110517 2024

  65. [66]

    J. Tang, Y. Gao, X. Li, J. Jia, Dpao-pfl: Dynamic parameter-aware optimization via continual learning for personalized federated learning, Electronics 14 (15) (2025).doi:10.3390/electronics14152945

    work page doi:10.3390/electronics14152945 2025

  66. [67]

    Z. Chen, S. Xu, Learning domain-heterogeneous speaker recognition sys- tems with personalized continual federated learning, EURASIP Journal on Audio, Speech, and Music Processing 2023 (1) (2023) 33.doi:https: //doi.org/10.1186/s13636-023-00299-2

    work page doi:10.1186/s13636-023-00299-2 2023

  67. [68]

    Zheng, J

    S. Zheng, J. Hu, G. Min, K. Li, Meta representation-based personalized federated continual learning in edge computing systems, IEEE Transac- tions on Computational Social Systems (2025) 1–12doi:10.1109/TCSS .2025.3582364

    work page doi:10.1109/tcss 2025

  68. [69]

    Zhong, W

    Z. Zhong, W. Bao, J. Wang, J. Chen, L. Lyu, W. Yang Bryan Lim, Sacfl: Self-adaptive federated continual learning for resource-constrained end devices, IEEE Transactions on Neural Networks and Learning Systems 36 (9) (2025) 17169–17183.doi:10.1109/TNNLS.2025.3565827

    work page doi:10.1109/tnnls.2025.3565827 2025

  69. [70]

    P. Wang, J. Wang, Z. Zhong, W. Bao, Y. Zhang, J. Chen, Enhancing long-term memory in federated class continual learning with lightweight adapters, Neurocomputing 656 (2025) 131459.doi:https://doi.org/ 10.1016/j.neucom.2025.131459

    work page doi:10.1016/j.neucom.2025.131459 2025

  70. [71]

    Iqbal, X

    S. Iqbal, X. Zhong, M. A. Khan, Z. Wu, D. A. AlHammadi, W. Liu, I. A. Choudhry, Hierarchical continual learning for domain-knowledge reten- tion in healthcare federated learning, IEEE Transactions on Consumer Electronics 71 (2) (2025) 5025–5035.doi:10.1109/TCE.2025.3563909

    work page doi:10.1109/tce.2025.3563909 2025

  71. [72]

    Luopan, R

    Y. Luopan, R. Han, Q. Zhang, X. Zuo, C. H. Liu, G. Wang, L. Y. Chen, Loci: Federated continual learning of heterogeneous tasks at edge, IEEE Transactions on Parallel and Distributed Systems 36 (4) (2025) 775–790. doi:10.1109/TPDS.2025.3531123. 73

    work page doi:10.1109/tpds.2025.3531123 2025

  72. [73]

    Shami, J

    S. Shami, J. Aberger, J. Pestana, B. Häcker, R. Sarc, M. Krisper, Feder- ated continual learning for vision-based plastic classification in recycling, Waste Management 205 (2025) 114976.doi:https://doi.org/10.101 6/j.wasman.2025.114976

    arXiv 2025

  73. [74]

    Carillo, F

    R. Carillo, F. Cerasuolo, G. Bovenzi, D. Ciuonzo, A. Pescapè, Explain- able federated class incremental learning for encrypted network traffic classification, Computer Networks (2025).doi:10.1016/j.comnet.2 025.111448

    work page doi:10.1016/j.comnet.2 2025

  74. [75]

    Z. Jin, J. Zhou, B. Li, X. Wu, C. Duan, Fl-iids: A novel federated learning-based incremental intrusion detection system, Future Genera- tion Computer Systems (2024).doi:10.1016/j.future.2023.09.019

    work page doi:10.1016/j.future.2023.09.019 2024

  75. [76]

    Iqbal, X

    S. Iqbal, X. Zhong, M. A. Khan, Z. Wu, D. A. Alhammadi, W. Liu, Family-based continual learning for multi-domain pattern analysis in federated frameworks with gcn and vit, Neural Networks 192 (2025) 107920.doi:https://doi.org/10.1016/j.neunet.2025.107920

    work page doi:10.1016/j.neunet.2025.107920 2025

  76. [77]

    F. E. Casado, D. Lema, M. F. Criado, et al., Concept drift detection and adaptation for federated and continual learning, Multimedia Tools and Applications81(2022)3397–3419.doi:10.1007/s11042-021-11219-x

    work page doi:10.1007/s11042-021-11219-x 2022

  77. [78]

    Sharma, V

    V. Sharma, V. K. R. Challa, P. Pranavi, R. P. Singh, Federated learning based gender classification in heterogeneous and distributed data having concept drift, Procedia Computer Science (2025).doi:10.1016/j.pr ocs.2024.12.033

    work page doi:10.1016/j.pr 2025

  78. [79]

    Augello, A

    A. Augello, A. D. Paola, G. L. Re, M2fd: Mobile malware federated detection under concept drift, Computers & Security (2025).doi:10.1 016/j.cose.2025.104361

    arXiv 2025

  79. [80]

    M. A. T. A. Elgalhud, M. N. Fekri, S. Mir, K. Grolinger, Federated online learning for adaptive load forecasting across decentralized nodes, International Journal of Electrical Power and Energy Systems (2025). doi:10.1016/j.ijepes.2025.110779

    work page doi:10.1016/j.ijepes.2025.110779 2025

  80. [81]

    Gelenbe, B

    E. Gelenbe, B. C. Gül, M. Nakıp, Disfida: Distributed self-supervised federated intrusion detection algorithm with online learning for health iot and iov, Internet of Things (2024).doi:10.1016/j.iot.2024.101 340. 74

    work page doi:10.1016/j.iot.2024.101 2024

Showing first 80 references.