mlsanityData to 14 Oct 2026

Using Diffusion Models as Generative Replay in Continual Federated Learning -- What will Happen?

arXiv 2411.06618 ↗First posted 10 Nov 2024cs.LG cs.DCcited by 2

On the map: Diffusion models → Robustness, privacy and adversarial aspects

Abstract (arXiv)

Federated learning (FL) has become a cornerstone in decentralized learning, where, in many scenarios, the incoming data distribution will change dynamically over time, introducing continuous learning (CL) problems. This continual federated learning (CFL) task presents unique challenges, particularly regarding catastrophic forgetting and non-IID input data. Existing solutions include using a replay buffer to store historical data or leveraging generative adversarial networks. Nevertheless, motivated by recent advancements in the diffusion model for generative tasks, this paper introduces DCFL, a novel framework tailored to address the challenges of CFL in dynamic distributed learning environments. Our approach harnesses the power of the conditional diffusion model to generate synthetic historical data at each local device during communication, effectively mitigating latent shifts in dynamic data distribution inputs. We provide the convergence bound for the proposed CFL framework and demonstrate its promising performance across multiple datasets, showcasing its effectiveness in tackling the complexities of CFL tasks.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Robustness, privacy and adversarial aspects, one of 14 directions in Diffusion models. Builds on 53 of its 63 references that are in the map. First posted on arXiv 10 Nov 2024.

Builds on

53 of 63 references.

References · 53

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  3. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  4. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  5. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  6. 2022Classifier-Free Diffusion Guidancecited by 5,847
  7. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  8. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  9. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  10. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
  11. 2019Advances and Open Problems in Federated Learningcited by 3,046
  12. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
38 more
  1. 2016Learning without Forgettingcited by 2,496
  2. 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 1,719
  3. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,229
  4. 2017Continual Learning with Deep Generative Replaycited by 1,158
  5. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,114
  6. 2017Memory Aware Synapses: Learning what (not) to forgetcited by 1,105
  7. 2018Experience Replay for Continual Learningcited by 1,095
  8. 2020Improved Techniques for Training Score-Based Generative Modelscited by 1,043
  9. 2017Deeper, Broader and Artier Domain Generalizationcited by 986
  10. 2021Blended Diffusion for Text-driven Editing of Natural Imagescited by 927
  11. 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 872
  12. 2017Lifelong Learning with Dynamically Expandable Networkscited by 694
  13. 2021Maximum Likelihood Training of Score-Based Diffusion Modelscited by 672
  14. 2016Conditional Image Synthesis With Auxiliary Classifier GANscited by 565
  15. 2019FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantizationcited by 356
  16. 2021SegDiff: Image Segmentation with Diffusion Probabilistic Modelscited by 280
  17. 2023Nearly d-Linear Convergence Bounds for Diffusion Models via Stochastic Localizationcited by 235
  18. 2017VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learningcited by 200
  19. 2023Score Approximation, Estimation and Distribution Recovery of Diffusion Models on Low-Dimensional Datacited by 174
  20. 2020Federated Continual Learning with Weighted Inter-client Transfercited by 161
  21. 2022Federated Class-Incremental Learningcited by 127
  22. 2023Decentralized Federated Learning: A Survey and Perspectivecited by 86
  23. 2019Toward Understanding Catastrophic Forgetting in Continual Learningcited by 68
  24. 2023TARGET: Federated Class-Continual Learning via Exemplar-Free Distillationcited by 65
  25. 2020Continual Adaptation of Visual Representations via Domain Randomization and Meta-learningcited by 55
  26. 2023Better Generative Replay for Continual Federated Learningcited by 55
  27. 2023A Data-Free Approach to Mitigate Catastrophic Forgetting in Federated Class Incremental Learning for Vision Taskscited by 41
  28. 2023Federated Learning for Computationally-Constrained Heterogeneous Devices: A Surveycited by 40
  29. 2020Dynamic Clustering in Federated Learningcited by 27
  30. 2023Every Parameter Matters: Ensuring the Convergence of Federated Learning with Dynamic Heterogeneous Models Reductioncited by 24
  31. 2023Federated Orthogonal Training: Mitigating Global Catastrophic Forgetting in Continual Federated Learningcited by 21
  32. 2023StableFDG: Style and Attention Based Learning for Federated Domain Generalizationcited by 21
  33. 2024Deep Generative Models for Offline Policy Learning: Tutorial, Survey, and Perspectives on Future Directionscited by 20
  34. 2022Federated Learning Challenges and Opportunities: An Outlookcited by 19
  35. 2023Peer-to-Peer Federated Continual Learning for Naturalistic Driving Action Recognitioncited by 19
  36. 2023Does Continual Learning Equally Forget All Parameters?cited by 18
  37. 2023DYNAMITE: Dynamic Interplay of Mini-Batch Size and Aggregation Frequency for Federated Learning with Static and Streaming Datasetcited by 14
  38. 2024Communication-Efficient Multimodal Federated Learning: Joint Modality and Client Selectioncited by 11

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 0; 2026: 1.

2 papers.

  1. 2024Unleashing the Power of Continual Learning on Non-Centralized Devices: A Surveycited by 23
  2. 2026Canonicalized Stable-List Replay for Private Federated Continual Learning over Language-Model Embeddingscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Diffusion-Driven Data Replay: A Novel Approach to Combat Forgetting in Federated Class Continual Learning
  2. 2025CCD: Continual Consistency Diffusion for Lifelong Generative Modeling
  3. 2024Joint Diffusion models in Continual Learning
  4. 2023Class-Prototype Conditional Diffusion Model with Gradient Projection for Continual Learning
  5. 2024Data-Free Federated Class Incremental Learning with Diffusion-Based Generative Memory
  6. 2023Continual Learning of Diffusion Models with Generative Distillation
  7. 2025Federated Learning for Diffusion Models
  8. 2024Stable Continual Reinforcement Learning via Diffusion-based Trajectory Replay