Federated continual learning: A comprehensive survey on lifelong and privacy-preserving learning over distributed and non-stationary data

2026-06-09

AI Summary

This work addresses the performance degradation, instability, and catastrophic forgetting that plague federated learning under non-stationary data streams by systematically investigating Federated Continual Learning (FCL)—a paradigm that integrates federated learning with continual learning to enable lifelong adaptation and privacy preservation in distributed settings. We formalize FCL through a rigorous definition and a multidimensional taxonomy, establish a unified research framework encompassing application scenarios, evaluation metrics, and experimental protocols, and provide a comprehensive analysis of key technical approaches, including privacy-preserving mechanisms, handling of client heterogeneity, and memory management strategies. By thoroughly reviewing existing methods and open challenges, this study offers a roadmap and recommendations for standardized benchmarks toward building robust and deployable FCL systems.

Abstract

Federated Learning (FL) enables collaborative and privacy-preserving model training across distributed clients, but most existing FL systems implicitly assume data stationarity. In real-world settings-such as healthcare, industrial IoT (IIOT), cybersecurity, and smart cities-data streams are inherently non-stationary, leading classical FL methods to suffer from performance degradation, instability, and catastrophic forgetting. Continual Learning (CL) addresses learning under evolving data distributions but has been largely studied in centralized settings, overlooking key constraints of federated systems, including privacy, limited communication, and client heterogeneity. Federated Continual Learning (FCL) emerges at the intersection of FL and CL, aiming to support lifelong, adaptive, and privacy-aware learning over distributed and non-stationary data. This survey provides a comprehensive and systematic overview of FCL. We first present a formal definition of the FCL problem and clarify its distinctive characteristics. We then analyze the limitations of classical FL under non-stationary conditions, highlighting how CL principles support long-term adaptation. To organize the rapidly growing literature, we propose a multi-dimensional taxonomy of FCL approaches. Furthermore, we review representative application domains and data modalities, summarize commonly used evaluation metrics, and discuss experimental perspectives for assessing long-term performance and forgetting. Finally, we highlight key open challenges, including handling extreme heterogeneity under temporal drift, designing scalable and privacy-preserving memory mechanisms, and establishing standardized benchmarks. This survey aims to serve as a reference and a roadmap for advancing FCL toward robust and deployable real-world systems.

Problem

• Federated Continual Learning
• non-stationary data
• privacy-preserving learning
• catastrophic forgetting
• distributed learning

Innovation

• Federated Continual Learning
• non-stationary data
• catastrophic forgetting
• privacy-preserving learning
• client heterogeneity