极端非独立同分布与全局类别不平衡下的联邦主动学习
Federated Active Learning Under Extreme Non-IID and Global Class Imbalance
在极端非独立同分布与全局类别不平衡下，用轻量预测差异推断全局不平衡度与本地-全局偏差，从而自适应选择全局或本地查询模型；这套「查询模型选择 + 原型引导伪标签 + 两阶段不确定性-多样性采样」可直接迁移到视觉主动学习的标注预算分配中。
原文依据 the model that achieves more class-balanced sampling, especially for minority classes, consistently leads to better final performance
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论联邦主动学习（FAL）旨在隐私约束下降低标注成本，但在存在严重全局类别不平衡且客户端高度异构的现实场景中，其有效性会下降。我们对 FAL 中的查询模型选择进行了系统研究，并得到一个核心洞见：能够实现更类别均衡采样（尤其是对少数类）的模型，始终带来更好的最终性能。此外，只有当全局分布高度不平衡且客户端数据相对同质时，全局模型查询才有益；否则本地模型更可取。基于这些发现，我们提出 FairFAL，一种自适应的类别公平 FAL 框架。FairFAL（1）通过轻量的预测差异推断全局不平衡与本地-全局偏差，从而在全局与本地查询模型之间自适应选择；（2）利用全局特征执行原型引导的伪标签，以促进类别感知的查询；（3）应用带 k-center 精炼的两阶段不确定性-多样性均衡采样策略。在五个基准上的实验表明，FairFAL 在具有挑战性的长尾与非独立同分布设置下持续优于最优方法。代码见 https://github.com/chenchenzong/FairFAL。
英文原文摘要 1305 字符
Federated active learning (FAL) seeks to reduce annotation cost under privacy constraints, yet its effectiveness degrades in realistic settings with severe global class imbalance and highly heterogeneous clients. We conduct a systematic study of query-model selection in FAL and uncover a central insight: the model that achieves more class-balanced sampling, especially for minority classes, consistently leads to better final performance. Moreover, global-model querying is beneficial only when the global distribution is highly imbalanced and client data are relatively homogeneous; otherwise, the local model is preferable. Based on these findings, we propose FairFAL, an adaptive class-fair FAL framework. FairFAL (1) infers global imbalance and local-global divergence via lightweight prediction discrepancy, enabling adaptive selection between global and local query models; (2) performs prototype-guided pseudo-labeling using global features to promote class-aware querying; and (3) applies a two-stage uncertainty-diversity balanced sampling strategy with k-center refinement. Experiments on five benchmarks show that FairFAL consistently outperforms state-of-the-art approaches under challenging long-tailed and non-IID settings. The code is available at https://github.com/chenchenzong/FairFAL.