# On the Convergence of Continual Federated Learning Using Incrementally Aggregated Gradients

arXiv: https://arxiv.org/abs/2411.07959 · HTML: https://mlsanity.com/paper/2411.07959/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 49 references that are in the map.
- First posted on arXiv 12 Nov 2024.

## Builds on (most cited first, 22 of 22)

- [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)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Experience Replay for Continual Learning](https://mlsanity.com/paper/1811.11682/) (2018)
- [Efficient Lifelong Learning with A-GEM](https://mlsanity.com/paper/1812.00420/) (2018)
- [A Comprehensive Survey of Continual Learning: Theory, Method and Application](https://mlsanity.com/paper/2302.00487/) (2023)
- [Federated Continual Learning with Weighted Inter-client Transfer](https://mlsanity.com/paper/2003.03196/) (2020)
- [On the Convergence of SGD with Biased Gradients](https://mlsanity.com/paper/2008.00051/) (2020)
- [TARGET: Federated Class-Continual Learning via Exemplar-Free Distillation](https://mlsanity.com/paper/2303.06937/) (2023)
- [Continual Learning for Real-World Autonomous Systems: Algorithms, Challenges and Frameworks](https://mlsanity.com/paper/2105.12374/) (2021)
- [No One Left Behind: Real-World Federated Class-Incremental Learning](https://mlsanity.com/paper/2302.00903/) (2023)
- [Federated Continual Learning via Knowledge Fusion: A Survey](https://mlsanity.com/paper/2312.16475/) (2023)
- [Continual Learning for Anomaly Detection in Surveillance Videos](https://mlsanity.com/paper/2004.07941/) (2020)
- [Avalanche: A PyTorch Library for Deep Continual Learning](https://mlsanity.com/paper/2302.01766/) (2023)
- [Towards Efficient Replay in Federated Incremental Learning](https://mlsanity.com/paper/2403.05890/) (2024)
- [Federated Orthogonal Training: Mitigating Global Catastrophic Forgetting in Continual Federated Learning](https://mlsanity.com/paper/2309.01289/) (2023)
- [Federated Reconnaissance: Efficient, Distributed, Class-Incremental Learning](https://mlsanity.com/paper/2109.00150/) (2021)
- [On the Convergence of Continual Learning with Adaptive Methods](https://mlsanity.com/paper/2404.05555/) (2024)
- [Coordinated Replay Sample Selection for Continual Federated Learning](https://mlsanity.com/paper/2310.15054/) (2023)

## Built on by (most cited first, 5 of 5)

- [Task-Agnostic Federated Continual Learning via Replay-Free Gradient Projection](https://mlsanity.com/paper/2509.21606/) (2025)
- [Theoretical Foundations of Continual Learning via Drift-Plus-Penalty](https://mlsanity.com/paper/2606.08452/) (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)
- [PMF-CL: Pareto-Minimal-Forgetting Continual Learner for Conflicting Tasks](https://mlsanity.com/paper/2605.19145/) (2026)
- [Federated Continual Learning as a Distributed Drift-Plus-Penalty Control Problem](https://mlsanity.com/paper/2608.21539/) (2026)

## Abstract (arXiv)

The holy grail of machine learning is to enable Continual Federated Learning (CFL) to enhance the efficiency, privacy, and scalability of AI systems while learning from streaming data. The primary challenge of a CFL system is to overcome global catastrophic forgetting, wherein the accuracy of the global model trained on new tasks declines on the old tasks. In this work, we propose Continual Federated Learning with Aggregated Gradients (C-FLAG), a novel replay-memory based federated strategy consisting of edge-based gradient updates on memory and aggregated gradients on the current data. We provide convergence analysis of the C-FLAG approach which addresses forgetting and bias while converging at a rate of O(1/√T) over T communication rounds. We formulate an optimization sub-problem that minimizes catastrophic forgetting, translating CFL into an iterative algorithm with adaptive learning rates that ensure seamless learning across tasks. We empirically show that C-FLAG outperforms several state-of-the-art baselines on both task and class-incremental settings with respect to metrics such as accuracy and forgetting.