mlsanityData to 7 Oct 2026

FeDMRA: Federated Incremental Learning with Dynamic Memory Replay Allocation

arXiv 2603.28455 ↗First posted 30 Mar 2026cs.LG cs.AI cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

In federated healthcare systems, Federated Class-Incremental Learning (FCIL) has emerged as a key paradigm, enabling continuous adaptive model learning among distributed clients while safeguarding data privacy. However, in practical applications, data across agent nodes within the distributed framework often exhibits non-independent and identically distributed (non-IID) characteristics, rendering traditional continual learning methods inapplicable. To address these challenges, this paper covers more comprehensive incremental task scenarios and proposes a dynamic memory allocation strategy for exemplar storage based on the data replay mechanism. This strategy fully taps into the inherent potential of data heterogeneity, while taking into account the performance fairness of all participating clients, thereby establishing a balanced and adaptive solution to mitigate catastrophic forgetting. Unlike the fixed allocation of client exemplar memory, the proposed scheme emphasizes the rational allocation of limited storage resources among clients to improve model performance. Furthermore, extensive experiments are conducted on three medical image datasets, and the results demonstrate significant performance improvements compared to existing baseline models.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 34 of its 56 references that are in the map. First posted on arXiv 30 Mar 2026.

Builds on

34 of 56 references.

References · 34

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  3. 2016Learning without Forgettingcited by 2,465
  4. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,313
  5. 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 860
  6. 2020Class-incremental learning: survey and performance evaluation on image classificationcited by 446
  7. 2021Data-Free Knowledge Distillation for Heterogeneous Federated Learningcited by 380
  8. 2022S-Prompts Learning with Pre-trained Transformers: An Occam's Razor for Domain Incremental Learningcited by 246
  9. 2022FOSTER: Feature Boosting and Compression for Class-Incremental Learningcited by 228
  10. 2023Heterogeneous Federated Learning: State-of-the-art and Research Challengescited by 160
  11. 2020Federated Visual Classification with Real-World Data Distributioncited by 126
  12. 2022Federated Class-Incremental Learningcited by 126
22 more
  1. 2021Semantic-aware Knowledge Distillation for Few-Shot Class-Incremental Learningcited by 114
  2. 2022Class-Incremental Learning by Knowledge Distillation with Adaptive Feature Consolidationcited by 113
  3. 2019Communication-Efficient Federated Deep Learning with Asynchronous Model Update and Temporally Weighted Aggregationcited by 99
  4. 2023Federated Learning for Medical Image Analysis: A Surveycited by 77
  5. 2024Continual Learning and Catastrophic Forgettingcited by 73
  6. 2022Few-Shot Class-Incremental Learning via Entropy-Regularized Data-Free Replaycited by 70
  7. 2021Essentials for Class Incremental Learningcited by 57
  8. 2023Better Generative Replay for Continual Federated Learningcited by 53
  9. 2023Fair Federated Medical Image Segmentation via Client Contribution Estimationcited by 50
  10. 2023A Data-Free Approach to Mitigate Catastrophic Forgetting in Federated Class Incremental Learning for Vision Taskscited by 41
  11. 2023FedNoRo: Towards Noise-Robust Federated Learning by Addressing Class Imbalance and Label Noise Heterogeneitycited by 33
  12. 2023Audio-Visual Class-Incremental Learningcited by 33
  13. 2024Towards Efficient Replay in Federated Incremental Learningcited by 33
  14. 2023Don't blame Dataset Shift! Shortcut Learning due to Gradients and Cross Entropycited by 30
  15. 2023Asynchronous Federated Continual Learningcited by 29
  16. 2022General Incremental Learning with Domain-aware Categorical Representationscited by 26
  17. 2024Diffusion-Driven Data Replay: A Novel Approach to Combat Forgetting in Federated Class Continual Learningcited by 23
  18. 2020Proxy Experience Replay: Federated Distillation for Distributed Reinforcement Learningcited by 10
  19. 2023A Continual Learning Approach for Cross-Domain White Blood Cell Classificationcited by 10
  20. 2022Multi-Granularity Regularized Re-Balancing for Class Incremental Learningcited by 8
  21. 2022FedER: Federated Learning through Experience Replay and Privacy-Preserving Data Synthesiscited by 4
  22. 2024Federated Distillation for Medical Image Classification: Towards Trustworthy Computer-Aided Diagnosiscited by 4

Built on by

Not cited yet.