Federated Learning (FL) of foundation and edge models increasingly targets deployments where client data distributions drift over time, yet existing forgetting-mitigation methods assume each client's distribution is stationary. Flashback, the strongest recent FL method against cross-client (spatial) forgetting, uses monotonically accumulating per-class label counts as a knowledge proxy; this proxy becomes miscalibrated under temporal distribution shift and anchors the global model to an outdated class balance. We formalise temporal forgetting in FL with a per-phase metric isolated from protocol-level fluctuations and propose Flashback Continual Learning (FlashbackCL), a drop-in extension of Flashback with (i) temporally-decayed label counts; (ii) a device-aware replay buffer with Class-Balanced Reservoir Sampling (CBRS); and (iii) server-side active coreset curation on the public distillation set. The results show that FlashbackCL achieves 6.9% to 10.0% relative improvement relative to Flashback, on CIFAR-10 with 50 clients and three controlled temporal shift modes, while simultaneously reducing temporal forgetting by up to 68%. A 5-variant ablation identifies CBRS replay as the critical component. FlashbackCL also improves Flashback by 3.5 points on stationary CIFAR-100, suggesting that class-balanced replay regularises spatial heterogeneity as well as temporal shift.

翻译：联邦学习（FL）在基础模型与边缘模型中的应用逐渐面向客户端数据分布随时间漂移的部署场景，然而现有的遗忘缓解方法均假设每个客户端的数据分布是平稳的。Flashback作为近期针对跨客户端（空间）遗忘最有效的FL方法，采用单调累积的每类标签计数作为知识代理；该代理在时间分布偏移下会失准，使全局模型锚定在过时的类别平衡上。我们通过独立于协议层面波动的逐阶段指标形式化定义了FL中的时间遗忘，并提出Flashback持续学习（FlashbackCL）——Flashback的一种即插即用扩展，包含：（i）时间衰减的标签计数；（ii）采用类别平衡水库采样（CBRS）的设备感知回放缓冲区；（iii）服务器端在公共蒸馏集上的主动核心集策展。结果表明，在包含50个客户端及三种受控时间偏移模式的CIFAR-10数据集上，FlashbackCL相较于Flashback实现了6.9%至10.0%的相对提升，同时将时间遗忘最多降低68%。通过5变体消融实验，CBRS回放被识别为关键组件。FlashbackCL在平稳CIFAR-100数据集上亦将Flashback提升3.5个百分点，表明类别平衡回放既能正则化时间偏移，也能正则化空间异质性。