arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.13485cs.LGstat.ML
收藏

基于图注意力的跨客户端可解释性非线性时序动态联邦学习

Federated Learning of Nonlinear Temporal Dynamics with Graph Attention-based Cross-Client Interpretability

Georgia Institute of Technology(佐治亚理工学院)

Ayse Tursucular, Ayush Mohanty, Nazal Mohamed, Nagi Gebraeel

AI总结:

本文提出了一种联邦学习框架,用于在分布式非线性系统中学习跨客户端的时序依赖关系。该框架通过非线性状态空间模型将本地高维观测映射到低维潜在状态,并利用图注意力网络在通信的潜在状态上学习图结构的神经状态转移模型,通过将学习的服务器侧转移模型的雅可比矩阵与注意力系数相关联,实现了对跨客户端时序依赖关系的可解释性。

摘要:

现代工业系统的网络越来越多地由分布式传感器监控,其中每个系统由多个子系统组成,生成高维时间序列数据。这些子系统通常是相互依赖的,因此理解一个子系统中的时序模式如何与其他子系统相关联变得很重要。在去中心化设置中,原始测量值无法共享,客户端观测是异质的,这使得问题更加复杂。在实际部署中,每个子系统(客户端)运行一个固定的专有模型,无法修改或重新训练,限制了现有方法。非线性动态进一步使跨客户端时序依赖关系难以解释,因为它们嵌入在非线性状态转移函数中。本文提出了一种联邦框架,用于在这些约束下学习跨客户端的时序依赖关系。每个客户端使用非线性状态空间模型将高维本地观测映射到低维潜在状态。中央服务器利用图注意力网络在通信的潜在状态上学习图结构的神经状态转移模型。为了可解释性,我们将学习的服务器侧转移模型的雅可比矩阵与注意力系数相关联,从而首次提供了对去中心化非线性系统中跨客户端时序依赖关系的可解释性描述。我们建立了理论收敛保证,以达到集中化 oracle,并通过合成实验验证了该框架,展示了收敛性、可解释性、可扩展性和隐私。此外,现实世界实验显示其性能与去中心化基线相当。

英文摘要:

Networks of modern industrial systems are increasingly monitored by distributed sensors, where each system comprises multiple subsystems that generate high-dimensional time-series. These subsystems are often interdependent, making it important to understand how temporal patterns observed at one subsystem relate to those observed across others. This problem is particularly challenging in decentralized settings where raw measurements cannot be shared, and client observations are heterogeneous. Moreover, in practice, each subsystem (client) operates a fixed, proprietary model that cannot be modified or retrained, limiting the applicability of existing approaches. Separately, nonlinear dynamics make cross-client temporal interdependencies difficult to characterize, as they are embedded implicitly within nonlinear state-transition functions. This paper presents a vertical federated learning framework for learning one-step-ahead cross-client temporal interdependencies under these constraints. Each client maps high-dimensional local observations to low-dimensional latent states using a nonlinear state-space model, while a Graph Attention Network (GAT)-based central server learns a state-transition model over the communicated states. Given a candidate graph skeleton, the server learns state-dependent attention coefficients that capture cross-client interactions. We analytically relate the GAT attention coefficients to the Jacobian of the learned state-transition model, yielding a first-order characterization of cross-client interdependencies. We further establish bounded closeness of the learned dynamics and Jacobians to a corresponding centralized oracle. Synthetic experiments validate the theoretical results on controlled systems with known graph skeletons. Experiments on real-world datasets with unknown graph skeletons demonstrate superior federated root cause analysis over baselines.

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。

↑