发表机构
School of Computer Science and Engineering, Soongsil University; School of Computing and Augmented Intelligence, Arizona State University（崇实大学计算机科学与工程学院; 亚利桑那州立大学计算与增强智能学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文针对联邦分层分类中存在的标签粒度偏差问题，提出FedBDFT方法，经实验验证该方法可显著提升严重标签粒度偏差下的鲁棒性，且能更好保留未见细粒度类别的分层表示。
AI 中文摘要
联邦学习支持在不集中本地数据的前提下实现分布式设备间的隐私保护协作。然而，客户端不仅可能存在数据分布差异，还可能在领域知识和标注能力上有所不同。本文提出了标签粒度偏差，这是联邦分层分类中一种新的统计异质性，指客户端在共享类别层次结构内提供不同详细程度的分类学一致标签。为了对这种异质性进行建模，我们使用概率关系邻居分类器生成客户端特定的局部标签层次结构，并通过基于轮廓系数的粗化构建WordNet引导的层次结构。我们的分析表明，强耦合的分层模型对不完整监督较为敏感，而条件softmax分类器则更具鲁棒性。基于这一见解，我们提出了分支解耦微调（Branch-wise Decoupled Fine-Tuning，BDFT）及其联邦版本FedBDFT，该方法对分支级分类器进行微调，并通过联邦优化对其进行聚合。在CIFAR-100、TinyImageNet和ImageNet上的实验表明，FedBDFT在严重标签粒度偏差下显著提升了鲁棒性，在偏差水平为0.6和0.9时，平均增益分别达到27.9%和56.4%。零样本结果进一步表明，FedBDFT能更好地为未见细粒度类别保留分层表示。这些发现证明了其在具有异构标签粒度的联邦分层分类中的有效性。
英文摘要
Federated learning enables privacy-preserving collaboration across distributed devices without centralizing local data. However, clients may differ not only in data distributions but also in domain knowledge and annotation capabilities. In this paper, we introduce label granularity skew, a new form of statistical heterogeneity in federated hierarchical classification, in which clients provide taxonomy-consistent labels at different levels of detail within a shared class hierarchy. To model this heterogeneity, we generate client-specific local label hierarchies using a probabilistic relational neighbor classifier and construct a WordNet-guided hierarchy via silhouette score-based coarsening. Our analysis shows that strongly coupled hierarchical models are sensitive to incomplete supervision, while the conditional softmax classifier is more robust. Based on this insight, we propose Branch-wise Decoupled Fine-Tuning (BDFT) and its federated version, FedBDFT, which fine-tune branch-wise classifiers and aggregate them through federated optimization. Experiments on CIFAR-100, TinyImageNet, and ImageNet show that FedBDFT substantially improves robustness under severe label granularity skew, with average gains of 27.9% and 56.4% at skewness levels of 0.6 and 0.9, respectively. Zero-shot results further indicate that FedBDFT better preserves hierarchical representations for unseen fine-grained classes. These findings demonstrate its effectiveness for federated hierarchical classification with heterogeneous label granularities.
