mlsanityData to 7 Oct 2026

FedProK: Trustworthy Federated Class-Incremental Learning via Prototypical Feature Knowledge Transfer

arXiv 2405.02685 ↗First posted 4 May 2024cs.LG cs.AI cs.NEcited by 9

Not on the map. Why?

Abstract (arXiv)

Federated Class-Incremental Learning (FCIL) focuses on continually transferring the previous knowledge to learn new classes in dynamic Federated Learning (FL). However, existing methods do not consider the trustworthiness of FCIL, i.e., improving continual utility, privacy, and efficiency simultaneously, which is greatly influenced by catastrophic forgetting and data heterogeneity among clients. To address this issue, we propose FedProK (Federated Prototypical Feature Knowledge Transfer), leveraging prototypical feature as a novel representation of knowledge to perform spatial-temporal knowledge transfer. Specifically, FedProK consists of two components: (1) feature translation procedure on the client side by temporal knowledge transfer from the learned classes and (2) prototypical knowledge fusion on the server side by spatial knowledge transfer among clients. Extensive experiments conducted in both synchronous and asynchronous settings demonstrate that our FedProK outperforms the other state-of-the-art methods in three perspectives of trustworthiness, validating its effectiveness in selectively transferring spatial-temporal knowledge.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 30 of its 51 references that are in the map. First posted on arXiv 4 May 2024.

Builds on

30 of 51 references.

References · 30

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  3. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  4. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,313
  5. 2019Deep Leakage from Gradientscited by 1,004
  6. 2020Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimizationcited by 897
  7. 2020Ensemble Distillation for Robust Model Fusion in Federated Learningcited by 678
  8. 2019Federated Learning with Personalization Layerscited by 533
  9. 2019Maintaining Discrimination and Fairness in Class Incremental Learningcited by 281
  10. 2020Threats to Federated Learning: A Surveycited by 171
  11. 2020Federated Continual Learning with Weighted Inter-client Transfercited by 158
  12. 2022Federated Class-Incremental Learningcited by 126
18 more
  1. 2022FeTrIL: Feature Translation for Exemplar-Free Class-Incremental Learningcited by 120
  2. 2022Vertical Federated Learning: Concepts, Advances and Challengescited by 104
  3. 2019Reliable Federated Learning for Mobile Networkscited by 92
  4. 2023TARGET: Federated Class-Continual Learning via Exemplar-Free Distillationcited by 64
  5. 2023On the Stability-Plasticity Dilemma of Class-Incremental Learningcited by 55
  6. 2023Federated Continual Learning via Knowledge Fusion: A Surveycited by 53
  7. 2020Federated Learning Meets Multi-objective Optimizationcited by 50
  8. 2018Multi-objective Evolutionary Federated Learningcited by 42
  9. 2022No Free Lunch Theorem for Security and Utility in Federated Learningcited by 39
  10. 2021Non-IID data and Continual Learning processes in Federated Learning: A long road aheadcited by 36
  11. 2022Trading Off Privacy, Utility and Efficiency in Federated Learningcited by 33
  12. 2023Asynchronous Federated Continual Learningcited by 29
  13. 2023GradMA: A Gradient-Memory-based Accelerated Federated Learning with Alleviated Catastrophic Forgettingcited by 27
  14. 2023A Survey for Federated Learning Evaluations: Goals and Measurescited by 16
  15. 2022Trustworthy Federated Learning via Blockchaincited by 15
  16. 2023Optimizing Privacy, Utility and Efficiency in Constrained Multi-Objective Federated Learningcited by 12
  17. 2023Fed-CPrompt: Contrastive Prompt for Rehearsal-Free Federated Continual Learningcited by 12
  18. 2022A Framework for Evaluating Privacy-Utility Trade-off in Vertical Federated Learningcited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 5; 2026: 1.

9 papers.

  1. 2024Unleashing the Power of Continual Learning on Non-Centralized Devices: A Surveycited by 23
  2. 2025Federated Continual Learning: Concepts, Challenges, and Solutionscited by 13
  3. 2025Class-wise Balancing Data Replay for Federated Class-Incremental Learningcited by 9
  4. 2024Handling Spatial-Temporal Data Heterogeneity for Federated Continual Learning via Tail Anchorcited by 8
  5. 2024Federated Class-Incremental Learning with Hierarchical Generative Prototypescited by 6
  6. 2025FedGPS: Statistical Rectification Against Data Heterogeneity in Federated Learningcited by 4
  7. 2025C^2Prompt: Class-aware Client Knowledge Interaction for Federated Continual Learningcited by 2
  8. 2025Task-agnostic Low-rank Residual Adaptation for Efficient Federated Continual Fine-Tuningcited by 1
  9. 2026Fisher-Routed Mixture of Experts for Federated Class-Incremental Learningcited by 0