# Towards Efficient Replay in Federated Incremental Learning

arXiv: https://arxiv.org/abs/2403.05890 · HTML: https://mlsanity.com/paper/2403.05890/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 50 references that are in the map.
- First posted on arXiv 9 Mar 2024.

## Builds on (most cited first, 30 of 31)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Moment Matching for Multi-Source Domain Adaptation](https://mlsanity.com/paper/1812.01754/) (2018)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [An Overview of Multi-Task Learning in Deep Neural Networks](https://mlsanity.com/paper/1706.05098/) (2017)
- [Ensemble Distillation for Robust Model Fusion in Federated Learning](https://mlsanity.com/paper/2006.07242/) (2020)
- [An Empirical Study of Example Forgetting during Deep Neural Network Learning](https://mlsanity.com/paper/1812.05159/) (2018)
- [Three scenarios for continual learning](https://mlsanity.com/paper/1904.07734/) (2019)
- [Deep Learning on a Data Diet: Finding Important Examples Early in Training](https://mlsanity.com/paper/2107.07075/) (2021)
- [Data-Free Knowledge Distillation for Heterogeneous Federated Learning](https://mlsanity.com/paper/2105.10056/) (2021)
- [PathNet: Evolution Channels Gradient Descent in Super Neural Networks](https://mlsanity.com/paper/1701.08734/) (2017)
- [Communication-Efficient On-Device Machine Learning: Federated Distillation and Augmentation under Non-IID Private Data](https://mlsanity.com/paper/1811.11479/) (2018)
- [Semantic Drift Compensation for Class-Incremental Learning](https://mlsanity.com/paper/2004.00440/) (2020)
- [Re-evaluating Continual Learning Scenarios: A Categorization and Case for Strong Baselines](https://mlsanity.com/paper/1810.12488/) (2018)
- [Federated Learning of a Mixture of Global and Local Models](https://mlsanity.com/paper/2002.05516/) (2020)
- [Federated Learning for Smart Healthcare: A Survey](https://mlsanity.com/paper/2111.08834/) (2021)
- [Fine-tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learning](https://mlsanity.com/paper/2203.09249/) (2022)
- [Federated Continual Learning with Weighted Inter-client Transfer](https://mlsanity.com/paper/2003.03196/) (2020)
- [Federated Class-Incremental Learning](https://mlsanity.com/paper/2203.11473/) (2022)
- [Continuous Learning in Single-Incremental-Task Scenarios](https://mlsanity.com/paper/1806.08568/) (2018)
- [Generative Feature Replay For Class-Incremental Learning](https://mlsanity.com/paper/2004.09199/) (2020)
- [Continual Learning with Node-Importance based Adaptive Group Sparse Regularization](https://mlsanity.com/paper/2003.13726/) (2020)
- [Better Generative Replay for Continual Federated Learning](https://mlsanity.com/paper/2302.13001/) (2023)
- [An Efficient Domain-Incremental Learning Approach to Drive in All Weather Conditions](https://mlsanity.com/paper/2204.08817/) (2022)
- [Non-IID data and Continual Learning processes in Federated Learning: A long road ahead](https://mlsanity.com/paper/2111.13394/) (2021)
- [Federated Learning with Position-Aware Neurons](https://mlsanity.com/paper/2203.14666/) (2022)
- [Domain-Incremental Continual Learning for Mitigating Bias in Facial Expression and Action Unit Recognition](https://mlsanity.com/paper/2103.08637/) (2021)

## Built on by (most cited first, 30 of 33)

- [Personalized Federated Domain-Incremental Learning based on Adaptive Knowledge Matching](https://mlsanity.com/paper/2407.05005/) (2024)
- [Ten Challenging Problems in Federated Foundation Models](https://mlsanity.com/paper/2502.12176/) (2025)
- [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)
- [Handling Spatial-Temporal Data Heterogeneity for Federated Continual Learning via Tail Anchor](https://mlsanity.com/paper/2412.18355/) (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)
- [On the Convergence of Continual Federated Learning Using Incrementally Aggregated Gradients](https://mlsanity.com/paper/2411.07959/) (2024)
- [Resource-Constrained Federated Continual Learning: What Does Matter?](https://mlsanity.com/paper/2501.08737/) (2025)
- [Feature Distillation is the Better Choice for Model-Heterogeneous Federated Learning](https://mlsanity.com/paper/2507.10348/) (2025)
- [C^2Prompt: Class-aware Client Knowledge Interaction for Federated Continual Learning](https://mlsanity.com/paper/2509.19674/) (2025)
- [Data Heterogeneity and Forgotten Labels in Split Federated Learning](https://mlsanity.com/paper/2511.09736/) (2025)
- [Better Knowledge Enhancement for Privacy-Preserving Cross-Project Defect Prediction](https://mlsanity.com/paper/2412.17317/) (2024)
- [Enhancing Federated Class-Incremental Learning via Spatial-Temporal Statistics Aggregation](https://mlsanity.com/paper/2506.01327/) (2025)
- [Improving Generalization in Heterogeneous Federated Continual Learning via Spatio-Temporal Gradient Matching with Prototypical Coreset](https://mlsanity.com/paper/2506.12031/) (2025)
- [FedTeddi: Temporal Drift and Divergence Aware Scheduling for Timely Federated Edge Learning](https://mlsanity.com/paper/2509.07342/) (2025)
- [FedBiF: Communication-Efficient Federated Learning via Bits Freezing](https://mlsanity.com/paper/2509.10161/) (2025)
- [Task-Agnostic Federated Continual Learning via Replay-Free Gradient Projection](https://mlsanity.com/paper/2509.21606/) (2025)
- [FedGTEA: Federated Class-Incremental Learning with Gaussian Task Embedding and Alignment](https://mlsanity.com/paper/2510.12927/) (2025)
- [Pathological Prior-Guided Multiple Instance Learning For Mitigating Catastrophic Forgetting in Breast Cancer Whole Slide Image Classification](https://mlsanity.com/paper/2503.06056/) (2025)
- [Asynchronous Federated Continual Segmentation with Evolving Clients and Label Spaces](https://mlsanity.com/paper/2503.15414/) (2025)
- [Harmonizing Generalization and Personalization in Ring-topology Decentralized Federated Learning](https://mlsanity.com/paper/2504.19103/) (2025)
- [A Scenario-Oriented Survey of Federated Recommender Systems: Techniques, Challenges, and Future Directions](https://mlsanity.com/paper/2508.19620/) (2025)
- [Gains: Fine-grained Federated Domain Adaptation in Open Set](https://mlsanity.com/paper/2510.15967/) (2025)
- [Federated Balanced Learning](https://mlsanity.com/paper/2601.14042/) (2026)
- [Server-Proximal Aggregation for Federated Domain-Incremental Learning under Partial Participation: Task-Uniform Convergence and Backward Transfer](https://mlsanity.com/paper/2601.22274/) (2026)
- [Catastrophic Forgetting Resilient One-Shot Incremental Federated Learning](https://mlsanity.com/paper/2602.17625/) (2026)
- [FeDMRA: Federated Incremental Learning with Dynamic Memory Replay Allocation](https://mlsanity.com/paper/2603.28455/) (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)
- [From Data Heterogeneity to Convergence: A Data-Centric Review of Federated Learning](https://mlsanity.com/paper/2606.10595/) (2026)

## Abstract (arXiv)

In Federated Learning (FL), the data in each client is typically assumed fixed or static. However, data often comes in an incremental manner in real-world applications, where the data domain may increase dynamically. In this work, we study catastrophic forgetting with data heterogeneity in Federated Incremental Learning (FIL) scenarios where edge clients may lack enough storage space to retain full data. We propose to employ a simple, generic framework for FIL named Re-Fed, which can coordinate each client to cache important samples for replay. More specifically, when a new task arrives, each client first caches selected previous samples based on their global and local importance. Then, the client trains the local model with both the cached samples and the samples from the new task. Theoretically, we analyze the ability of Re-Fed to discover important samples for replay thus alleviating the catastrophic forgetting problem. Moreover, we empirically show that Re-Fed achieves competitive performance compared to state-of-the-art methods.