Decentralized Dynamic Cooperation of Personalized Models for Federated Continual Learning
Not on the map. Why?
Abstract (arXiv)
Federated continual learning (FCL) has garnered increasing attention for its ability to support distributed computation in environments with evolving data distributions. However, the emergence of new tasks introduces both temporal and cross-client shifts, making catastrophic forgetting a critical challenge. Most existing works aggregate knowledge from clients into a global model, which may not enhance client performance since irrelevant knowledge could introduce interference, especially in heterogeneous scenarios. Additionally, directly applying decentralized approaches to FCL suffers from ineffective group formation caused by task changes. To address these challenges, we propose a decentralized dynamic cooperation framework for FCL, where clients establish dynamic cooperative learning coalitions to balance the acquisition of new knowledge and the retention of prior learning, thereby obtaining personalized models. To maximize model performance, each client engages in selective cooperation, dynamically allying with others who offer meaningful performance gains. This results in non-overlapping, variable coalitions at each stage of the task. Moreover, we use coalitional affinity game to simulate coalition relationships between clients. By assessing both client gradient coherence and model similarity, we quantify the client benefits derived from cooperation. We also propose a merge-blocking algorithm and a dynamic cooperative evolution algorithm to achieve cooperative and dynamic equilibrium. Comprehensive experiments demonstrate the superiority of our method compared to various baselines. Code is available at: https://github.com/ydn3229/DCFCL.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 27 of its 49 references that are in the map. First posted on arXiv 28 Sep 2025.
Builds on
27 of 49 references.
References · 27
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
- 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
- 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
- 2018Federated Optimization in Heterogeneous Networkscited by 2,987
- 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,333
- 2017Continual Learning with Deep Generative Replaycited by 1,158
- 2020Federated Learning with Matched Averagingcited by 564
- 2019Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraintscited by 503
- 2020Personalized Federated Learning: A Meta-Learning Approachcited by 312
- 2021Personalized Federated Learning using Hypernetworkscited by 212
- 2020Federated Continual Learning with Weighted Inter-client Transfercited by 161
15 more
- 2022DisPFL: Towards Communication-Efficient Personalized Federated Learning via Decentralized Sparse Trainingcited by 74
- 2020Model-sharing Games: Analyzing Federated Learning Under Voluntary Participationcited by 60
- 2023Revisiting Weighted Aggregation in Federated Learning with Neural Networkscited by 58
- 2023Better Generative Replay for Continual Federated Learningcited by 55
- 2023Federated Continual Learning via Knowledge Fusion: A Surveycited by 53
- 2020FedGroup: Efficient Clustered Federated Learning via Decomposed Data-Driven Measurecited by 46
- 2021A distillation-based approach integrating continual learning and federated learning for pervasive servicescited by 42
- 2021Optimality and Stability in Federated Learning: A Game-theoretic Approachcited by 40
- 2021Cross-Gradient Aggregation for Decentralized Learning from Non-IID datacited by 33
- 2023Asynchronous Federated Continual Learningcited by 29
- 2021Collaboration Equilibrium in Federated Learningcited by 16
- 2025Accurate Forgetting for Heterogeneous Federated Continual Learningcited by 11
- 2025Learning without Isolation: Pathway Protection for Continual Learningcited by 6
- 2022A Coalition Formation Game Approach for Personalized Federated Learningcited by 2
- 2024FPPL: An Efficient and Non-IID Robust Federated Continual Learning Frameworkcited by 2
Built on by
Citing papers per year: 2026: 2.
2 papers.