# Diffusion-Driven Data Replay: A Novel Approach to Combat Forgetting in Federated Class Continual Learning

arXiv: https://arxiv.org/abs/2409.01128 · HTML: https://mlsanity.com/paper/2409.01128/

## Key facts

- Cited by 23 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 55 of its 68 references that are in the map.
- First posted on arXiv 2 Sep 2024.

## Placed in

- Diffusion models / [Robustness, privacy and adversarial aspects](https://mlsanity.com/diffusion/robustness-privacy-and-adversarial-aspects/)

## Builds on (most cited first, 30 of 55)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://mlsanity.com/paper/2208.01618/) (2022)
- [LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs](https://mlsanity.com/paper/2111.02114/) (2021)
- [Progressive Neural Networks](https://mlsanity.com/paper/1606.04671/) (2016)
- [Imagic: Text-Based Real Image Editing with Diffusion Models](https://mlsanity.com/paper/2210.09276/) (2022)
- [Memory Aware Synapses: Learning what (not) to forget](https://mlsanity.com/paper/1711.09601/) (2017)
- [Experience Replay for Continual Learning](https://mlsanity.com/paper/1811.11682/) (2018)
- [Deep Leakage from Gradients](https://mlsanity.com/paper/1906.08935/) (2019)
- [PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning](https://mlsanity.com/paper/1711.05769/) (2017)
- [Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence](https://mlsanity.com/paper/1801.10112/) (2018)
- [Lifelong Learning with Dynamically Expandable Networks](https://mlsanity.com/paper/1708.01547/) (2017)
- [The Medical Segmentation Decathlon](https://mlsanity.com/paper/2106.05735/) (2021)
- [Gradient based sample selection for online continual learning](https://mlsanity.com/paper/1903.08671/) (2019)
- [Conditional Image Synthesis With Auxiliary Classifier GANs](https://mlsanity.com/paper/1610.09585/) (2016)
- [Federated Learning with Differential Privacy: Algorithms and Performance Analysis](https://mlsanity.com/paper/1911.00222/) (2019)
- [The Liver Tumor Segmentation Benchmark (LiTS)](https://mlsanity.com/paper/1901.04056/) (2019)
- [Continual learning with hypernetworks](https://mlsanity.com/paper/1906.00695/) (2019)
- [Overcoming Catastrophic Forgetting by Incremental Moment Matching](https://mlsanity.com/paper/1703.08475/) (2017)
- [Data-Free Learning of Student Networks](https://mlsanity.com/paper/1904.01186/) (2019)
- [Federated Learning for Smart Healthcare: A Survey](https://mlsanity.com/paper/2111.08834/) (2021)

## Built on by (most cited first, 23 of 23)

- [One-Shot Diffusion Mimicker for Handwritten Text Generation](https://mlsanity.com/paper/2409.04004/) (2024)
- [Federated Continual Learning: Concepts, Challenges, and Solutions](https://mlsanity.com/paper/2502.07059/) (2025)
- [Beyond Isolated Words: Diffusion Brush for Handwritten Text-Line Generation](https://mlsanity.com/paper/2508.03256/) (2025)
- [Handling Spatial-Temporal Data Heterogeneity for Federated Continual Learning via Tail Anchor](https://mlsanity.com/paper/2412.18355/) (2024)
- [ReplayCAD: Generative Diffusion Replay for Continual Anomaly Detection](https://mlsanity.com/paper/2505.06603/) (2025)
- [Class-wise Balancing Data Replay for Federated Class-Incremental Learning](https://mlsanity.com/paper/2507.07712/) (2025)
- [FedGPS: Statistical Rectification Against Data Heterogeneity in Federated Learning](https://mlsanity.com/paper/2510.20250/) (2025)
- [C^2Prompt: Class-aware Client Knowledge Interaction for Federated Continual Learning](https://mlsanity.com/paper/2509.19674/) (2025)
- [Order-Level Attention Similarity Across Language Models: A Latent Commonality](https://mlsanity.com/paper/2511.05064/) (2025)
- [Task-Agnostic Federated Continual Learning via Replay-Free Gradient Projection](https://mlsanity.com/paper/2509.21606/) (2025)
- [Exploring the Impact of Parameter Update Magnitude on Forgetting and Generalization of Continual Learning](https://mlsanity.com/paper/2602.20796/) (2026)
- [OrbitNVS: Harnessing Video Diffusion Priors for Novel View Synthesis](https://mlsanity.com/paper/2603.19613/) (2026)
- [Disentangling data distribution for Federated Learning](https://mlsanity.com/paper/2410.12530/) (2024)
- [Task-Agnostic Federation over Decentralized Data: Research Landscape and Visions](https://mlsanity.com/paper/2503.03140/) (2025)
- [KDC-Diff: A Latent-Aware Diffusion Model with Knowledge Retention for Memory-Efficient Image Generation](https://mlsanity.com/paper/2505.06995/) (2025)
- [FeDMRA: Federated Incremental Learning with Dynamic Memory Replay Allocation](https://mlsanity.com/paper/2603.28455/) (2026)
- [Temporal Memory for Resource-Constrained Agents: Continual Learning via Stochastic Compress-Add-Smooth](https://mlsanity.com/paper/2604.00067/) (2026)
- [From Selection to Scheduling: Federated Geometry-Aware Correction Makes Exemplar Replay Work Better under Continual Dynamic Heterogeneity](https://mlsanity.com/paper/2604.08617/) (2026)
- [Canonicalized Stable-List Replay for Private Federated Continual Learning over Language-Model Embeddings](https://mlsanity.com/paper/2606.00426/) (2026)
- [From Data Heterogeneity to Convergence: A Data-Centric Review of Federated Learning](https://mlsanity.com/paper/2606.10595/) (2026)
- [When Generator Replay Degrades: Projected Rehearsal Orchestration for Heterogeneous Federated Class-Incremental Learning](https://mlsanity.com/paper/2606.15695/) (2026)
- [Code Division Modulation Layers Against Forgetting and Inference in Continual Gait Identification](https://mlsanity.com/paper/2607.19122/) (2026)
- [Federated Continual Learning as a Distributed Drift-Plus-Penalty Control Problem](https://mlsanity.com/paper/2608.21539/) (2026)

## Abstract (arXiv)

Federated Class Continual Learning (FCCL) merges the challenges of distributed client learning with the need for seamless adaptation to new classes without forgetting old ones. The key challenge in FCCL is catastrophic forgetting, an issue that has been explored to some extent in Continual Learning (CL). However, due to privacy preservation requirements, some conventional methods, such as experience replay, are not directly applicable to FCCL. Existing FCCL methods mitigate forgetting by generating historical data through federated training of GANs or data-free knowledge distillation. However, these approaches often suffer from unstable training of generators or low-quality generated data, limiting their guidance for the model. To address this challenge, we propose a novel method of data replay based on diffusion models. Instead of training a diffusion model, we employ a pre-trained conditional diffusion model to reverse-engineer each class, searching the corresponding input conditions for each class within the model's input space, significantly reducing computational resources and time consumption while ensuring effective generation. Furthermore, we enhance the classifier's domain generalization ability on generated and real data through contrastive learning, indirectly improving the representational capability of generated data for real data. Comprehensive experiments demonstrate that our method significantly outperforms existing baselines. Code is available at https://github.com/jinglin-liang/DDDR.