解决联邦多标签学习中标签关联不一致问题，提升跨客户端协作效果。
FedHarmony: Harmonizing Heterogeneous Label Correlations in Federated Multi-Label Learning
- 引入全局共识关联作为教师信号，修正各客户端的局部关联偏差。
- 根据数据量和关联质量动态加权聚合，提升模型收敛性与精度。
- 在真实联邦数据集上显著优于现有方法，适合医疗、推荐等隐私敏感场景。
联邦多标签学习是一种分布式范式，多个客户端在不共享原始数据的前提下，基于异构的多标签数据进行协同学习。然而，在异构分布下建模标签关联仍具挑战：由于客户端标签空间不同且共现模式各异，各客户端学习到的关联结构会偏离全局结构，我们称之为标签关联漂移。为此，本文提出FedHarmony框架，通过引入共识关联（consensus correlation）捕捉客户端间的一致性，作为全局教师信号以纠正局部估计偏差。在聚合阶段，系统同时考量客户端的数据规模与关联质量，动态分配权重。此外，设计了加速优化算法，并理论证明其收敛速度更快而精度不降。在真实世界联邦多标签数据集上的实验表明，FedHarmony持续优于当前最优方法。
原文摘要 · Abstract (English)
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 other 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 for FedHarmony 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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。