联邦持续学习：概念、挑战与解决方案
Federated Continual Learning: Concepts, Challenges, and Solutions
AI总结：
本综述全面回顾了联邦持续学习（FCL）在动态环境下面临的异构性、模型稳定性、通信开销和隐私保护等关键挑战，并整合联邦学习与持续学习的见解提出了提升系统有效性与可扩展性的策略。
摘要：
联邦持续学习（Federated Continual Learning, FCL）已成为动态环境中协作模型训练的稳健解决方案，在这些环境中，数据样本不断生成并分布在多个设备上。本综述对FCL进行了全面回顾，重点关注异构性、模型稳定性、通信开销和隐私保护等关键挑战。我们探讨了各种形式的异构性及其对模型性能的影响。为了展示处理异构数据分布的复杂性，本文回顾了针对非独立同分布（non-IID）数据、资源受限平台和个性化学习的解决方案。接下来，我们回顾了确保模型稳定性和避免灾难性遗忘的技术，这些在非平稳环境中至关重要。隐私保护技术是FCL的另一个方面，本文也进行了回顾。本综述整合了联邦学习和持续学习的见解，提出了提高FCL系统有效性和可扩展性的策略，使其适用于广泛的现实场景。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
