面向时空预测的个性化联邦学习：一种基于双重语义对齐的对比方法
Personalized Federated Learning for Spatio-Temporal Forecasting: A Dual Semantic Alignment-Based Contrastive Approach
AI总结：
针对时空预测中的时空异质性与联邦个性化难题，提出FUELS双重语义对齐对比学习方法，通过时间难负样本过滤和空间定制原型提升性能并降低约94%通信成本。
摘要：
现有的时空预测联邦学习（FL）方法无法捕捉内在的时空异质性，这需要个性化联邦学习（PFL）方法来建模随时空变化的模式。尽管对比学习方法在解决时空异质性方面很有前景，但现有方法在确定负样本对方面效果不佳，且难以应用于PFL范式。为解决这一局限，我们提出了一种名为Federated dUal sEmantic aLignment-based contraStive learning（FUELS）的新型PFL方法，该方法能够基于语义相似度自适应地对齐正负样本对，从而通过辅助对比任务将精确的时空异质性注入潜在表示空间。从时间角度看，引入了难负样本过滤模块，为补充的客户端内对比任务动态对齐异构时间表示。从空间角度看，我们设计了轻量且高效的原型作为客户端级语义表示，服务器基于这些原型评估空间相似度，并为补充的客户端间对比任务生成客户端定制的全局原型。大量实验表明，FUELS优于最先进的方法，同时通信成本降低约94%。
英文摘要：
The existing federated learning (FL) methods for spatio-temporal forecasting fail to capture the inherent spatio-temporal heterogeneity, which calls for personalized FL (PFL) methods to model the spatio-temporally variant patterns. While contrastive learning approach is promising in addressing spatio-temporal heterogeneity, the existing methods are noneffective in determining negative pairs and can hardly apply to PFL paradigm. To tackle this limitation, we propose a novel PFL method, named Federated dUal sEmantic aLignment-based contraStive learning (FUELS), which can adaptively align positive and negative pairs based on semantic similarity, thereby injecting precise spatio-temporal heterogeneity into the latent representation space by auxiliary contrastive tasks. From temporal perspective, a hard negative filtering module is introduced to dynamically align heterogeneous temporal representations for the supplemented intra-client contrastive task. From spatial perspective, we design lightweight-but-efficient prototypes as client-level semantic representations, based on which the server evaluates spatial similarity and yields client-customized global prototypes for the supplemented inter-client contrastive task. Extensive experiments demonstrate that FUELS outperforms state-of-the-art methods, with communication cost decreasing by around 94%.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
