# Better Generative Replay for Continual Federated Learning

arXiv: https://arxiv.org/abs/2302.13001 · HTML: https://mlsanity.com/paper/2302.13001/

## Key facts

- Cited by 55 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 44 references that are in the map.
- First posted on arXiv 25 Feb 2023.

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

- [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)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Continual Learning with Deep Generative Replay](https://mlsanity.com/paper/1705.08690/) (2017)
- [Federated Learning with Non-IID Data](https://mlsanity.com/paper/1806.00582/) (2018)
- [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)
- [Dark Experience for General Continual Learning: a Strong, Simple Baseline](https://mlsanity.com/paper/2004.07211/) (2020)
- [LEAF: A Benchmark for Federated Settings](https://mlsanity.com/paper/1812.01097/) (2018)
- [Lifelong Learning with Dynamically Expandable Networks](https://mlsanity.com/paper/1708.01547/) (2017)
- [Three scenarios for continual learning](https://mlsanity.com/paper/1904.07734/) (2019)
- [Conditional Image Synthesis With Auxiliary Classifier GANs](https://mlsanity.com/paper/1610.09585/) (2016)
- [Data-Free Knowledge Distillation for Heterogeneous Federated Learning](https://mlsanity.com/paper/2105.10056/) (2021)
- [Federated Learning on Non-IID Data: A Survey](https://mlsanity.com/paper/2106.06843/) (2021)
- [Understanding the Role of Training Regimes in Continual Learning](https://mlsanity.com/paper/2006.06958/) (2020)
- [FedBE: Making Bayesian Model Ensemble Applicable to Federated Learning](https://mlsanity.com/paper/2009.01974/) (2020)
- [Federated Continual Learning with Weighted Inter-client Transfer](https://mlsanity.com/paper/2003.03196/) (2020)
- [Towards Understanding Knowledge Distillation](https://mlsanity.com/paper/2105.13093/) (2021)
- [Adversarial Continual Learning](https://mlsanity.com/paper/2003.09553/) (2020)
- [Federated Class-Incremental Learning](https://mlsanity.com/paper/2203.11473/) (2022)
- [Stabilizing Training of Generative Adversarial Networks through Regularization](https://mlsanity.com/paper/1705.09367/) (2017)
- [FedGAN: Federated Generative Adversarial Networks for Distributed Data](https://mlsanity.com/paper/2006.07228/) (2020)
- [Rebooting ACGAN: Auxiliary Classifier GANs with Stable Training](https://mlsanity.com/paper/2111.01118/) (2021)
- [A distillation-based approach integrating continual learning and federated learning for pervasive services](https://mlsanity.com/paper/2109.04197/) (2021)
- [Improving GAN Training with Probability Ratio Clipping and Sample Reweighting](https://mlsanity.com/paper/2006.06900/) (2020)
- [Federated Reconnaissance: Efficient, Distributed, Class-Incremental Learning](https://mlsanity.com/paper/2109.00150/) (2021)
- [Training Federated GANs with Theoretical Guarantees: A Universal Aggregation Approach](https://mlsanity.com/paper/2102.04655/) (2021)

## Built on by (most cited first, 30 of 55)

- [A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learning](https://mlsanity.com/paper/2307.09218/) (2023)
- [A Data-Free Approach to Mitigate Catastrophic Forgetting in Federated Class Incremental Learning for Vision Tasks](https://mlsanity.com/paper/2311.07784/) (2023)
- [Federated Incremental Semantic Segmentation](https://mlsanity.com/paper/2304.04620/) (2023)
- [Towards Efficient Replay in Federated Incremental Learning](https://mlsanity.com/paper/2403.05890/) (2024)
- [Diffusion-Driven Data Replay: A Novel Approach to Combat Forgetting in Federated Class Continual Learning](https://mlsanity.com/paper/2409.01128/) (2024)
- [Unleashing the Power of Continual Learning on Non-Centralized Devices: A Survey](https://mlsanity.com/paper/2412.13840/) (2024)
- [Federated Orthogonal Training: Mitigating Global Catastrophic Forgetting in Continual Federated Learning](https://mlsanity.com/paper/2309.01289/) (2023)
- [Personalized Federated Domain-Incremental Learning based on Adaptive Knowledge Matching](https://mlsanity.com/paper/2407.05005/) (2024)
- [PILoRA: Prototype Guided Incremental LoRA for Federated Class-Incremental Learning](https://mlsanity.com/paper/2401.02094/) (2024)
- [Rehearsal-Free Continual Federated Learning with Synergistic Synaptic Intelligence](https://mlsanity.com/paper/2412.13779/) (2024)
- [Federated Continual Learning: Concepts, Challenges, and Solutions](https://mlsanity.com/paper/2502.07059/) (2025)
- [Accurate Forgetting for Heterogeneous Federated Continual Learning](https://mlsanity.com/paper/2502.14205/) (2025)
- [Towards Continual Learning Desiderata via HSIC-Bottleneck Orthogonalization and Equiangular Embedding](https://mlsanity.com/paper/2401.09067/) (2024)
- [Class-wise Balancing Data Replay for Federated Class-Incremental Learning](https://mlsanity.com/paper/2507.07712/) (2025)
- [SacFL: Self-Adaptive Federated Continual Learning for Resource-Constrained End Devices](https://mlsanity.com/paper/2505.00365/) (2025)
- [Continual Adaptation of Vision Transformers for Federated Learning](https://mlsanity.com/paper/2306.09970/) (2023)
- [Adapter-based Selective Knowledge Distillation for Federated Multi-domain Meeting Summarization](https://mlsanity.com/paper/2308.03275/) (2023)
- [Continual Offline Reinforcement Learning via Diffusion-based Dual Generative Replay](https://mlsanity.com/paper/2404.10662/) (2024)
- [Solving Continual Offline RL through Selective Weights Activation on Aligned Spaces](https://mlsanity.com/paper/2410.15698/) (2024)
- [Federated Continual Learning Goes Online: Uncertainty-Aware Memory Management for Vision Tasks and Beyond](https://mlsanity.com/paper/2405.18925/) (2024)
- [Resource-Constrained Federated Continual Learning: What Does Matter?](https://mlsanity.com/paper/2501.08737/) (2025)
- [Don't Memorize; Mimic The Past: Federated Class Incremental Learning Without Episodic Memory](https://mlsanity.com/paper/2307.00497/) (2023)
- [Federated Continual Novel Class Learning](https://mlsanity.com/paper/2312.13500/) (2023)
- [Overcoming Catastrophic Forgetting in Federated Class-Incremental Learning via Federated Global Twin Generator](https://mlsanity.com/paper/2407.11078/) (2024)
- [Data-Free Federated Class Incremental Learning with Diffusion-Based Generative Memory](https://mlsanity.com/paper/2405.17457/) (2024)
- [Masked Autoencoders are Parameter-Efficient Federated Continual Learners](https://mlsanity.com/paper/2411.01916/) (2024)
- [Reminding Multimodal Large Language Models of Object-aware Knowledge with Retrieved Tags](https://mlsanity.com/paper/2406.10839/) (2024)
- [PIP: Prototypes-Injected Prompt for Federated Class Incremental Learning](https://mlsanity.com/paper/2407.20705/) (2024)
- [FPPL: An Efficient and Non-IID Robust Federated Continual Learning Framework](https://mlsanity.com/paper/2411.01904/) (2024)
- [Using Diffusion Models as Generative Replay in Continual Federated Learning -- What will Happen?](https://mlsanity.com/paper/2411.06618/) (2024)

## Abstract (arXiv)

Federated learning is a technique that enables a centralized server to learn from distributed clients via communications without accessing the client local data. However, existing federated learning works mainly focus on a single task scenario with static data. In this paper, we introduce the problem of continual federated learning, where clients incrementally learn new tasks and history data cannot be stored due to certain reasons, such as limited storage and data retention policy. Generative replay based methods are effective for continual learning without storing history data, but adapting them for this setting is challenging. By analyzing the behaviors of clients during training, we find that the unstable training process caused by distributed training on non-IID data leads to a notable performance degradation. To address this problem, we propose our FedCIL model with two simple but effective solutions: model consolidation and consistency enforcement. Our experimental results on multiple benchmark datasets demonstrate that our method significantly outperforms baselines.