作为分布式漂移加惩罚控制问题的联邦持续学习
Federated Continual Learning as a Distributed Drift-Plus-Penalty Control Problem
浏览论文内容
中文总结 AI 辅助
本研究将联邦持续学习建模为分布式漂移加惩罚控制问题，提出FedQCL框架，通过虚拟队列调控遗忘，在多基准上优于现有方法并降低异质数据下的遗忘。
中文摘要 AI 辅助
联邦持续学习（Federated Continual Learning, FCL）是现实世界分布式学习系统的基础，要求模型在客户端间适应顺序性、非独立同分布（non-IID）数据，同时缓解灾难性遗忘与客户端漂移。现有方法将持续学习（Continual Learning, CL）建模为一系列针对每个客户端的本地单任务优化问题，通过重放、正则化或基于投影的约束等启发式机制，结合聚合实现。然而，FCL中的遗忘本质上是长期分布式现象，源于时序任务演化与跨客户端异质性的相互作用，未得到显式调控。本研究将FCL建模为随机控制问题，提出基于李雅普诺夫漂移加惩罚（drift-plus-penalty, DPP）优化的联邦队列调控持续学习框架（Federated Queue-regulated Continual Learning, FedQCL）。FedQCL引入虚拟队列追踪跨任务与客户端的遗忘积累，实现对稳定性-可塑性权衡的显式控制。通过优化DPP目标，该方法可同时提升当前任务性能，而基于队列的公式提供了可解释且可调的机制，通过单一参数平衡适应性与保留能力，无需梯度投影或额外通信开销。在Split-CIFAR-10、Split-CIFAR-100和Split-TinyImageNet等标准基准上的实证评估表明，FedQCL在准确率上优于现有最优基线，且在异质数据分布下显著降低了遗忘。
英文摘要
Federated Continual Learning (FCL) is fundamental to real-world distributed learning systems, requiring models to adapt to sequential, non-IID data across clients while mitigating catastrophic forgetting and client drift. Existing approaches formulate continual learning (CL) as a sequence of per-task optimization problems, applied locally at each client and coupled through aggregation, using heuristic mechanisms such as replay, regularization, or projection-based constraints. However, forgetting in FCL is inherently a long-term, distributed phenomenon, arising from the interaction of temporal task evolution and cross-client heterogeneity, which is not explicitly regulated. In this work, we cast FCL as a stochastic control problem and propose Federated Queue-regulated Continual Learning (FedQCL), a framework based on Lyapunov drift-plus-penalty (DPP) optimization. FedQCL introduces virtual queues to track the accumulation of forgetting across tasks and clients, enabling explicit control of the stability-plasticity trade-off. By optimizing a DPP objective, the method jointly improves current-task performance while the queue-based formulation provides an interpretable and tunable mechanism to balance adaptation and retention through a single parameter, without requiring gradient projection or additional communication overhead. Empirical evaluations on standard benchmarks, including Split-CIFAR-10, Split-CIFAR-100, and Split-TinyImageNet, demonstrate that FedQCL outperforms state-of-the-art baselines with respect to accuracy while significantly reducing forgetting under heterogeneous data distributions.
发表机构
- IIIT Delhi（德里印度信息技术学院）
- IIT Dharwad（达尔瓦德印度理工学院）
机构由 AI 辅助整理，请以论文原文为准。
