FedGRC：面向联邦学习的几何共识个性化框架
Is High Local Accuracy Enough? Geometric Consensus with Support-Adaptive Statistical Personalization for Federated Learning
这篇论文做了个 FedGRC 框架，专治联邦学习里本地准确率高但稀有类翻车的问题，在 CIFAR-10/100 和 FedRS 上比 21 个基线都强。
arXiv 论文提出 FedGRC，一个统一泛化与个性化的联邦学习（PFL）框架。作者指出高本地准确率会掩盖稀有类和未见类上的失败，因此提出补充全局、稀有类、未见类评估的评测协议。框架包含 CGRL 表示学习、MMS 共享度量构建和 SASP 收缩个性化三个模块。在 CIFAR-10 和 CIFAR-100 上，FedGRC 的全局识别与个性化底线比 SOTA 基线至少高 2.17% 和 2.13%；在真实异构的 FedRS 数据集上，本地适应、全局识别和个性化底线分别超过最佳基线 2.15%、3.30% 和 4.61%。实验对比了 3 个数据集、5 种异构设置下的 21 种方法。
Is High Local Accuracy Enough? Geometric Consensus with Support-Adaptive Statistical Personalization for Federated Learning
Real-world deployment of personalized federated learning (PFL) requires adapting to heterogeneous clients while preserving recognition performance beyond local distributions. However, high local accuracy can conceal failures on locally rare or absent classes. Effective personalization should therefore strengthen global recognition while raising the personalization floor. We propose an evaluation protocol that complements local accuracy with global, rare-class, and unseen-class evaluations to reveal generalization obscured by local scores, and assesses personalization floors among the worst-performing clients to expose weaknesses hidden by aggregate performance. To meet these deployment challenges, we propose FedGRC, a unified PFL framework integrating generalization and personalization through (i) Consensus-Guided Representation Learning (CGRL), which learns discriminative representations through shared directional and magnitude guidance; (ii) Multilayer Metric Synthesis (MMS), which constructs a shared covariance metric from these multilayer representations for statistical classification; and (iii) Support-Adaptive Shrinkage Personalization (SASP), which adapts class means within this metric by shrinking local estimates toward shared means according to local sample support, enabling adaptation while retaining shared knowledge. Extensive experiments, including benchmarking against 21 methods across 5 heterogeneity settings on 3 datasets and comprehensive ablation studies, validate the effectiveness of FedGRC. On CIFAR-10 and CIFAR-100, FedGRC surpasses state-of-the-art (SOTA) baselines in global recognition and personalization floors by at least 2.17% and 2.13%, respectively. On the real-world heterogeneous FedRS dataset, it outperforms the respective best baselines by 2.15%, 3.30%, and 4.61% in local adaptation, global recognition, and the personalization floor.
