← 研踪 PaperTrailCVF · CVPR 2026:cvf:d4d91d9de46e8d53caacc762a0487680 · 记录 #1
FedHarmony: Harmonizing Heterogeneous Label Correlations in Federated Multi-Label Learning
Kou, ZhiqiangWu, JunxiangHuang, WenkeHe, WenwenXie, Ming-KunWang, ChangweiJia, YuhengJiang, DiLiu, YangGeng, XinYang, Qiang 来源日期（仅到年份） 2026
来源记录日期 2026
雷达观测 2026-11-05 01:23
摘要
Federated Multi-Label Learning is a distributed paradigm where multiple clients possess heterogeneous multi-label data and perform collaborative learning under privacy constraints without sharing raw data. However, modeling label correlations under heterogeneous distributions remains challenging. Due to client-specific label spaces and varying co-occurrence patterns, correlations learned by individual clients inevitably deviate from the global structure, a phenomenon we term label correlation drift. To address this, we propose FedHarmony, a framework that harmonizes heterogeneous label correlations across clients. It introduces consensus correlation, capturing agreement among clients and serving as a global teacher to correct biased local estimates. During aggregation, FedHarmony evaluates each client by both data size and correlation quality, assigning weights accordingly. Moreover, we develop an accelerated optimization algorithm and theoretically establish faster convergence without sacrificing accuracy. Experiments on real-world federated multi-label datasets show that FedHarmony consistently outperforms state-of-the-art methods.
论文发现出处
这些页面提供论文线索，不代表同行评审或质量认证。
观测到的版本
平台记录号代表本站观测到的元数据变化，不是作者修订号。来源日期仅到月份或年份时，按该月或该年首日存档。
记录 #1 · 2026 · 最新观测版本
FedHarmony: Harmonizing Heterogeneous Label Correlations in Federated Multi-Label Learning
Federated Multi-Label Learning is a distributed paradigm where multiple clients possess heterogeneous multi-label data and perform collaborative learning under privacy constraints without sharing raw data. However, modeling label correlations under heterogeneous distributions remains challenging. Due to client-specific label spaces and varying co-occurrence patterns, correlations learned by individual clients inevitably deviate from the global structure, a phenomenon we term label correlation drift. To address this, we propose FedHarmony, a framework that harmonizes heterogeneous label correlations across clients. It introduces consensus correlation, capturing agreement among clients and serving as a global teacher to correct biased local estimates. During aggregation, FedHarmony evaluates each client by both data size and correlation quality, assigning weights accordingly. Moreover, we develop an accelerated optimization algorithm and theoretically establish faster convergence without sacrificing accuracy. Experiments on real-world federated multi-label datasets show that FedHarmony consistently outperforms state-of-the-art methods.
查看此版本解读 →查看此版本原文 ↗