paper-with-me

Papers

Federated Continual Learning: Concepts, Challenges, and Solutions

2025-02-10 · Parisa Hamedi, Roozbeh Razavi-Far, Ehsan Hallaji

Federated Continual Learning (FCL) has emerged as a robust solution for collaborative model training in dynamic environments, where data samples are continuously generated and distributed across multiple devices. This survey provides a comprehensive review of FCL, focusing on key challenges such as heterogeneity, model stability, communication overhead, and privacy preservation. We explore various forms of heterogeneity and their impact on model performance. Solutions to non-IID data, resource-constrained platforms, and personalized learning are reviewed in an effort to show the complexities of handling heterogeneous data distributions. Next, we review techniques for ensuring model stability and avoiding catastrophic forgetting, which are critical in non-stationary environments. Privacy-preserving techniques are another aspect of FCL that have been reviewed in this work. This survey has integrated insights from federated learning and continual learning to present strategies for improving the efficacy and scalability of FCL systems, making it applicable to a wide range of real-world scenarios.

📄 PDF Abstract BibTeX arXiv:2502.07059

Code (0)

등록된 구현이 없습니다.

Tasks

Continual LearningFederated LearningPrivacy PreservingSurvey

Similar Papers 제목 키워드 기반

FedRewind: Rewinding Continual Model Exchange for Decentralized Federated Learning

2024-11-14 · Luca Palazzo, Matteo Pennisi, Federica Proietto Salanitri, Giovanni Bellitto 외

In this paper, we present FedRewind, a novel approach to decentralized federated learning that leverages model exchange among nodes to address the issue of data distribution shift. Drawing inspiration from continual lear…

Continual LearningFederated Learning

Concept Matching: Clustering-based Federated Continual Learning

2023-11-12 · Xiaopeng Jiang, Cristian Borcea

Federated Continual Learning (FCL) has emerged as a promising paradigm that combines Federated Learning (FL) and Continual Learning (CL). To achieve good model accuracy, FCL needs to tackle catastrophic forgetting due to…

ClusteringContinual LearningFederated Learning

Federated Continual Learning for Edge-AI: A Comprehensive Survey

2024-11-20 · Zi Wang, Fei Wu, Feng Yu, Yurui Zhou 외

Edge-AI, the convergence of edge computing and artificial intelligence (AI), has become a promising paradigm that enables the deployment of advanced AI models at the network edge, close to users. In Edge-AI, federated co…

Continual LearningEdge-computingSurvey

Incentive-Based Federated Learning: Architectural Elements and Future Directions

2025-10-16 · Chanuka A. S. Hewa Kaluannakkage, Rajkumar Buyya arxiv

Federated learning promises to revolutionize machine learning by enabling collaborative model training without compromising data privacy. However, practical adaptability can be limited by critical factors, such as the pa…

Reinforcement LearningFederated Learning

Using Diffusion Models as Generative Replay in Continual Federated Learning -- What will Happen?

2024-11-10 · Yongsheng Mei, Liangqi Yuan, Dong-Jun Han, Kevin S. Chan 외

Federated learning (FL) has become a cornerstone in decentralized learning, where, in many scenarios, the incoming data distribution will change dynamically over time, introducing continuous learning (CL) problems. This …

Federated Learning