mlsanityData to 14 Oct 2026

TARGET: Federated Class-Continual Learning via Exemplar-Free Distillation

arXiv 2303.06937 ↗First posted 13 Mar 2023cs.LG cs.AIcited by 65

Not on the map. Why?

Abstract (arXiv)

This paper focuses on an under-explored yet important problem: Federated Class-Continual Learning (FCCL), where new classes are dynamically added in federated learning. Existing FCCL works suffer from various limitations, such as requiring additional datasets or storing the private data from previous tasks. In response, we first demonstrate that non-IID data exacerbates catastrophic forgetting issue in FL. Then we propose a novel method called TARGET (federatTed clAss-continual leaRninG via Exemplar-free disTillation), which alleviates catastrophic forgetting in FCCL while preserving client data privacy. Our proposed method leverages the previously trained global model to transfer knowledge of old tasks to the current task at the model level. Moreover, a generator is trained to produce synthetic data to simulate the global distribution of data on each client at the data level. Compared to previous FCCL methods, TARGET does not require any additional datasets or storing real data from previous tasks, which makes it ideal for data-sensitive scenarios.

Key facts. Cited by 65 papers in the map (data through 14 Oct 2026). Builds on 46 of its 68 references that are in the map. First posted on arXiv 13 Mar 2023.

Builds on

46 of 68 references.

References · 46

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  4. 2019Advances and Open Problems in Federated Learningcited by 3,046
  5. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  6. 2016Learning without Forgettingcited by 2,496
  7. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,333
  8. 2017Gradient Episodic Memory for Continual Learningcited by 1,898
  9. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
  10. 2018Continual Lifelong Learning with Neural Networks: A Reviewcited by 1,330
  11. 2017Continual Learning with Deep Generative Replaycited by 1,158
  12. 2018Federated Learning with Non-IID Datacited by 1,108
34 more
  1. 2018Efficient Lifelong Learning with A-GEMcited by 1,058
  2. 2018Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigencecited by 742
  3. 2013An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networkscited by 722
  4. 2017Lifelong Learning with Dynamically Expandable Networkscited by 694
  5. 2018Overcoming catastrophic forgetting with hard attention to the taskcited by 681
  6. 2018Federated Learning for Mobile Keyboard Predictioncited by 572
  7. 2018Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interferencecited by 521
  8. 2019Dreaming to Distill: Data-free Knowledge Transfer via DeepInversioncited by 423
  9. 2017Measuring Catastrophic Forgetting in Neural Networkscited by 360
  10. 2019Maintaining Discrimination and Fairness in Class Incremental Learningcited by 283
  11. 2017Overcoming Catastrophic Forgetting by Incremental Moment Matchingcited by 243
  12. 2022FOSTER: Feature Boosting and Compression for Class-Incremental Learningcited by 229
  13. 2015Federated Optimization:Distributed Optimization Beyond the Datacentercited by 195
  14. 2018Reinforced Continual Learningcited by 186
  15. 2019Class-incremental Learning via Deep Model Consolidationcited by 173
  16. 2020Federated Continual Learning with Weighted Inter-client Transfercited by 161
  17. 2021Always Be Dreaming: A New Approach for Data-Free Class-Incremental Learningcited by 131
  18. 2022Federated Class-Incremental Learningcited by 127
  19. 2019Scalable and Order-robust Continual Learning with Additive Parameter Decompositioncited by 125
  20. 2022Federated Learning with Label Distribution Skew via Logits Calibrationcited by 109
  21. 2021DENSE: Data-Free One-Shot Federated Learningcited by 100
  22. 2020Continual Learning in Low-rank Orthogonal Subspacescited by 99
  23. 2023RMM: Reinforced Memory Management for Class-Incremental Learningcited by 66
  24. 2020CPR: Classifier-Projection Regularization for Continual Learningcited by 62
  25. 2023Revisiting Weighted Aggregation in Federated Learning with Neural Networkscited by 58
  26. 2021Essentials for Class Incremental Learningcited by 57
  27. 2021A distillation-based approach integrating continual learning and federated learning for pervasive servicescited by 42
  28. 2021Concept drift detection and adaptation for federated and continual learningcited by 32
  29. 2021Data-Free Knowledge Transfer: A Surveycited by 31
  30. 2018Partitioned Variational Inference: A unified framework encompassing federated and continual learningcited by 29
  31. 2021FedSpeech: Federated Text-to-Speech with Continual Learningcited by 16
  32. 2021Tackling Dynamics in Federated Incremental Learning with Variational Embedding Rehearsalcited by 11
  33. 2022Federated Continual Learning for Text Classification via Selective Inter-client Transfercited by 9
  34. 2018Closed-Loop Memory GAN for Continual Learningcited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 24; 2025: 21; 2026: 19.

65 papers.

Sort:

By area:

  1. 2024DiffClass: Diffusion-Based Class Incremental Learningcited by 23
  2. 2024Diffusion-Driven Data Replay: A Novel Approach to Combat Forgetting in Federated Class Continual Learningcited by 23
  3. 2024Unleashing the Power of Continual Learning on Non-Centralized Devices: A Surveycited by 23
  4. 2024Closed-form merging of parameter-efficient modules for Federated Continual Learningcited by 22
  5. 2023Federated Orthogonal Training: Mitigating Global Catastrophic Forgetting in Continual Federated Learningcited by 21
  6. 2024Personalized Federated Domain-Incremental Learning based on Adaptive Knowledge Matchingcited by 21
  7. 2024PILoRA: Prototype Guided Incremental LoRA for Federated Class-Incremental Learningcited by 19
  8. 2024Text-Enhanced Data-free Approach for Federated Class-Incremental Learningcited by 16
  9. 2024Federated Distillation: A Surveycited by 15
  10. 2024Rehearsal-Free Continual Federated Learning with Synergistic Synaptic Intelligencecited by 15
  11. 2025Federated Continual Learning: Concepts, Challenges, and Solutionscited by 13
  12. 2025Does Training with Synthetic Data Truly Protect Privacy?cited by 12
38 more
  1. 2025Federated Continual Instruction Tuningcited by 12
  2. 2024FedProK: Trustworthy Federated Class-Incremental Learning via Prototypical Feature Knowledge Transfercited by 9
  3. 2024Handling Spatial-Temporal Data Heterogeneity for Federated Continual Learning via Tail Anchorcited by 9
  4. 2025Federated Class-Incremental Learning: A Hybrid Approach Using Latent Exemplars and Data-Free Techniques to Address Local and Global Forgettingcited by 9
  5. 2025Class-wise Balancing Data Replay for Federated Class-Incremental Learningcited by 9
  6. 2025SacFL: Self-Adaptive Federated Continual Learning for Resource-Constrained End Devicescited by 8
  7. 2024COALA: A Practical and Vision-Centric Federated Learning Platformcited by 7
  8. 2024Federated Class-Incremental Learning with Hierarchical Generative Prototypescited by 6
  9. 2024On the Convergence of Continual Federated Learning Using Incrementally Aggregated Gradientscited by 5
  10. 2024Federated Continual Graph Learningcited by 5
  11. 2025Resource-Constrained Federated Continual Learning: What Does Matter?cited by 5
  12. 2025Feature Distillation is the Better Choice for Model-Heterogeneous Federated Learningcited by 5
  13. 2024Rehearsal-free Federated Domain-incremental Learningcited by 4
  14. 2024Overcoming Catastrophic Forgetting in Federated Class-Incremental Learning via Federated Global Twin Generatorcited by 4
  15. 2026Contrastive Continual Learning for Model Adaptability in Internet of Thingscited by 4
  16. 2024Data-Free Federated Class Incremental Learning with Diffusion-Based Generative Memorycited by 3
  17. 2024Masked Autoencoders are Parameter-Efficient Federated Continual Learnerscited by 3
  18. 2024Review of Mathematical Optimization in Federated Learningcited by 3
  19. 2025AFCL: Analytic Federated Continual Learning for Spatio-Temporal Invariance of Non-IID Datacited by 3
  20. 2024FPPL: An Efficient and Non-IID Robust Federated Continual Learning Frameworkcited by 2
  21. 2024Using Diffusion Models as Generative Replay in Continual Federated Learning -- What will Happen?cited by 2
  22. 2024Exemplar-condensed Federated Class-incremental Learningcited by 2
  23. 2025Federated-Continual Dynamic Segmentation of Histopathology guided by Barlow Continuitycited by 2
  24. 2025C^2Prompt: Class-aware Client Knowledge Interaction for Federated Continual Learningcited by 2
  25. 2025Task-agnostic Low-rank Residual Adaptation for Efficient Federated Continual Fine-Tuningcited by 1
  26. 2025Enhancing Federated Class-Incremental Learning via Spatial-Temporal Statistics Aggregationcited by 1
  27. 2025Improving Generalization in Heterogeneous Federated Continual Learning via Spatio-Temporal Gradient Matching with Prototypical Coresetcited by 1
  28. 2025Task-Agnostic Federated Continual Learning via Replay-Free Gradient Projectioncited by 1
  29. 2025FedGTEA: Federated Class-Incremental Learning with Gaussian Task Embedding and Alignmentcited by 1
  30. 2025Helmsman: Autonomous Synthesis of Federated Learning Systems via Collaborative LLM Agentscited by 1
  31. 2026CRAD: Class-wise Reliability-Aware Distillation for Decentralized Heterogeneous Federated Learningcited by 1
  32. 2024Few-Shot Class-Incremental Learning with Non-IID Decentralized Datacited by 0
  33. 2025Asynchronous Federated Continual Segmentation with Evolving Clients and Label Spacescited by 0
  34. 2025Dynamic Allocation Hypernetwork with Adaptive Model Recalibration for FCLcited by 0
  35. 2025Large-Small Model Collaborative Framework for Federated Continual Learningcited by 0
  36. 2025DOLFIN: Balancing Stability and Plasticity in Federated Continual Learningcited by 0
  37. 2026Federated Continual Learning for Privacy-Preserving Hospital Imaging Classificationcited by 0
  38. 2026Server-Proximal Aggregation for Federated Domain-Incremental Learning under Partial Participation: Task-Uniform Convergence and Backward Transfercited by 0

50 most cited of 65 All 65 (JSON)