从选择到调度：联邦几何感知校正让样本回放在持续动态异构下更有效
From Selection to Scheduling: Federated Geometry-Aware Correction Makes Exemplar Replay Work Better under Continual Dynamic Heterogeneity
用固定的等角紧框架原型作为跨客户端共享的类判别参考结构，并通过成对角度相似性对齐做结构知识蒸馏，这一思路可直接迁移到视觉模型在类不平衡或非独立同分布数据下的表征漂移抑制与少样本类特征保护。
原文依据 aligning the pairwise angular similarities between feature representations and their corresponding Equiangular Tight Frame prototypes
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论样本回放已成为联邦持续学习（FCL）中缓解灾难性遗忘的有效策略，其做法是保留过去任务中的代表性样本。现有研究侧重于设计样本重要性估计机制以识别信息丰富的样本，但通常忽视了如何有效利用所选样本的策略，这限制了它们在客户端与任务间持续动态异构条件下的性能。为解决该问题，本文提出一种联邦几何感知校正方法，称为 FEAT，用以缓解由不平衡引发的表征坍缩——该现象会将稀有类特征拉向跨客户端的频繁类。具体而言，该方法包含两个关键模块：1）几何结构对齐模块通过将特征表示之间的成对角度相似性与对应的等角紧框架原型对齐，执行结构知识蒸馏；这些原型固定且在客户端间共享，作为类判别性参考结构。这促进了跨任务的几何一致性，并有助于缓解表征漂移；2）基于能量的几何校正模块从特征嵌入中移除与任务无关的方向分量，从而减少对多数类的预测偏置。这提升了对少数类的敏感性，并增强了模型在类不平衡数据分布下的鲁棒性。在三个基准数据集上的大量实验表明，与九种最优方法相比，FEAT 在 Top-1 准确率上取得了 4%–8% 的显著提升。
英文原文摘要 1650 字符
Exemplar replay has become an effective strategy for mitigating catastrophic forgetting in federated continual learning (FCL) by retaining representative samples from past tasks. Existing studies focus on designing sample-importance estimation mechanisms to identify information-rich samples. However, they typically overlook strategies for effectively utilizing the selected exemplars, which limits their performance under continual dynamic heterogeneity across clients and tasks. To address this issue, this paper proposes a federated geometry-aware correction method, termed FEAT, which alleviates imbalance-induced representation collapse that drags rare-class features toward frequent classes across clients. Specifically, it consists of two key modules: 1) the Geometric Structure Alignment module performs structural knowledge distillation by aligning the pairwise angular similarities between feature representations and their corresponding Equiangular Tight Frame prototypes, which are fixed and shared across clients to serve as a class-discriminative reference structure. This encourages geometric consistency across tasks and helps mitigate representation drift; 2) the Energy-based Geometric Correction module removes task-irrelevant directional components from feature embeddings, which reduces prediction bias toward majority classes. This improves sensitivity to minority classes and enhances the model's robustness under class-imbalanced data distributions. Extensive experiments on three benchmark datasets demonstrate that FEAT substantially achieves a 4%-8% improvement in Top-1 accuracy compared to nine state-of-the-art methods.