Federated Class-Incremental Learning (FCIL) enables Class-Incremental Learning (CIL) from distributed data. Existing FCIL methods typically integrate old knowledge preservation into local client training. However, these methods cannot avoid spatial-temporal client drift caused by data heterogeneity and often incur significant computational and communication overhead, limiting practical deployment. To address these challenges simultaneously, we propose a novel approach, Spatial-Temporal Statistics Aggregation (STSA), which provides a unified framework to aggregate feature statistics both spatially (across clients) and temporally (across stages). The aggregated feature statistics are unaffected by data heterogeneity and can be used to update the classifier in closed form at each stage. Additionally, we introduce STSA-E, a communication-efficient variant with theoretical guarantees, achieving similar performance to STSA-E with much lower communication overhead. Extensive experiments on three widely used FCIL datasets, with varying degrees of data heterogeneity, show that our method outperforms state-of-the-art FCIL methods in terms of performance, flexibility, and both communication and computation efficiency. The code is available at https://github.com/Yuqin-G/STSA.

翻译：联邦类增量学习（FCIL）实现了从分布式数据中进行类增量学习（CIL）。现有的FCIL方法通常将旧知识保留整合到本地客户端训练中。然而，这些方法无法避免由数据异构性引起的时空客户端漂移，并且常常产生显著的计算和通信开销，限制了实际部署。为了同时应对这些挑战，我们提出了一种新颖的方法——时空统计聚合（STSA），它提供了一个统一的框架，用于在空间上（跨客户端）和时间上（跨阶段）聚合特征统计量。聚合后的特征统计量不受数据异构性的影响，并可用于在每个阶段以闭式解更新分类器。此外，我们引入了STSA-E，这是一个具有理论保证的通信高效变体，能以远低于STSA的通信开销实现与STSA相当的性能。在三个广泛使用的FCIL数据集上，针对不同程度的数据异构性进行的广泛实验表明，我们的方法在性能、灵活性以及通信和计算效率方面均优于最先进的FCIL方法。代码可在 https://github.com/Yuqin-G/STSA 获取。