# SacFL: Self-Adaptive Federated Continual Learning for Resource-Constrained End Devices

arXiv: https://arxiv.org/abs/2505.00365 · HTML: https://mlsanity.com/paper/2505.00365/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 69 references that are in the map.
- First posted on arXiv 1 May 2025.

## Builds on (most cited first, 30 of 37)

- [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)
- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020)
- [On the Convergence of FedAvg on Non-IID Data](https://mlsanity.com/paper/1907.02189/) (2019)
- [A Comprehensive Survey of Continual Learning: Theory, Method and Application](https://mlsanity.com/paper/2302.00487/) (2023)
- [Model-Contrastive Federated Learning](https://mlsanity.com/paper/2103.16257/) (2021)
- [Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates](https://mlsanity.com/paper/1803.01498/) (2018)
- [Federated Learning with Matched Averaging](https://mlsanity.com/paper/2002.06440/) (2020)
- [Federated Learning with Personalization Layers](https://mlsanity.com/paper/1912.00818/) (2019)
- [FedMD: Heterogenous Federated Learning via Model Distillation](https://mlsanity.com/paper/1910.03581/) (2019)
- [Agnostic Federated Learning](https://mlsanity.com/paper/1902.00146/) (2019)
- [Federated Learning in Mobile Edge Networks: A Comprehensive Survey](https://mlsanity.com/paper/1909.11875/) (2019)
- [Personalized Federated Learning: A Meta-Learning Approach](https://mlsanity.com/paper/2002.07948/) (2020)
- [Learning without Memorizing](https://mlsanity.com/paper/1811.08051/) (2018)
- [Client-Edge-Cloud Hierarchical Federated Learning](https://mlsanity.com/paper/1905.06641/) (2019)
- [Federated Continual Learning with Weighted Inter-client Transfer](https://mlsanity.com/paper/2003.03196/) (2020)
- [Federated Evaluation of On-device Personalization](https://mlsanity.com/paper/1910.10252/) (2019)
- [Federated Class-Incremental Learning](https://mlsanity.com/paper/2203.11473/) (2022)
- [Generative Feature Replay For Class-Incremental Learning](https://mlsanity.com/paper/2004.09199/) (2020)
- [Federated Learning for Generalization, Robustness, Fairness: A Survey and Benchmark](https://mlsanity.com/paper/2311.06750/) (2023)
- [HFEL: Joint Edge Association and Resource Allocation for Cost-Efficient Hierarchical Federated Edge Learning](https://mlsanity.com/paper/2002.11343/) (2020)
- [TARGET: Federated Class-Continual Learning via Exemplar-Free Distillation](https://mlsanity.com/paper/2303.06937/) (2023)
- [Better Generative Replay for Continual Federated Learning](https://mlsanity.com/paper/2302.13001/) (2023)
- [Federated Continual Learning via Knowledge Fusion: A Survey](https://mlsanity.com/paper/2312.16475/) (2023)
- [Generalizable Heterogeneous Federated Cross-Correlation and Instance Similarity Learning](https://mlsanity.com/paper/2309.16286/) (2023)
- [Randomized Distributed Mean Estimation: Accuracy vs Communication](https://mlsanity.com/paper/1611.07555/) (2016)
- [Towards Efficient Replay in Federated Incremental Learning](https://mlsanity.com/paper/2403.05890/) (2024)

## Built on by (most cited first, 8 of 8)

- [Class-wise Balancing Data Replay for Federated Class-Incremental Learning](https://mlsanity.com/paper/2507.07712/) (2025)
- [Privacy-Aware Continual Self-Supervised Learning on Multi-Window Chest Computed Tomography for Domain-Shift Robustness](https://mlsanity.com/paper/2510.27213/) (2025)
- [Federated continual learning: A comprehensive survey on lifelong and privacy-preserving learning over distributed and non-stationary data](https://mlsanity.com/paper/2606.11272/) (2026)
- [Gains: Fine-grained Federated Domain Adaptation in Open Set](https://mlsanity.com/paper/2510.15967/) (2025)
- [RPP: A Certified Poisoned-Sample Detection Framework for Backdoor Attacks under Dataset Imbalance](https://mlsanity.com/paper/2602.00183/) (2026)
- [Accurate and Resource-Efficient Federated Continual Learning](https://mlsanity.com/paper/2606.11480/) (2026)
- [FedUP: One-Shot Federated Unlearning via Centroid-Guided Plug-in Filters](https://mlsanity.com/paper/2606.24113/) (2026)
- [Fisher-Routed Mixture of Experts for Federated Class-Incremental Learning](https://mlsanity.com/paper/2606.28835/) (2026)

## Abstract (arXiv)

The proliferation of end devices has led to a distributed computing paradigm, wherein on-device machine learning models continuously process diverse data generated by these devices. The dynamic nature of this data, characterized by continuous changes or data drift, poses significant challenges for on-device models. To address this issue, continual learning (CL) is proposed, enabling machine learning models to incrementally update their knowledge and mitigate catastrophic forgetting. However, the traditional centralized approach to CL is unsuitable for end devices due to privacy and data volume concerns. In this context, federated continual learning (FCL) emerges as a promising solution, preserving user data locally while enhancing models through collaborative updates. Aiming at the challenges of limited storage resources for CL, poor autonomy in task shift detection, and difficulty in coping with new adversarial tasks in FCL scenario, we propose a novel FCL framework named SacFL. SacFL employs an Encoder-Decoder architecture to separate task-robust and task-sensitive components, significantly reducing storage demands by retaining lightweight task-sensitive components for resource-constrained end devices. Moreover, rmSacFL leverages contrastive learning to introduce an autonomous data shift detection mechanism, enabling it to discern whether a new task has emerged and whether it is a benign task. This capability ultimately allows the device to autonomously trigger CL or attack defense strategy without additional information, which is more practical for end devices. Comprehensive experiments conducted on multiple text and image datasets, such as Cifar100 and THUCNews, have validated the effectiveness of rmSacFL in both class-incremental and domain-incremental scenarios. Furthermore, a demo system has been developed to verify its practicality.