发表机构
The Hong Kong University of Science and Technology (Guangzhou); Shanghai Jiao Tong University; Harbin Engineering University（香港科技大学（广州）; 上海交通大学; 哈尔滨工程大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对时空预测，提出联邦去混淆框架\method，将客户端视为不同因果环境，利用客户端异质性作为分布式环境证据，学习全局原型码本捕获共享环境模式，推导理论边界，实验证明其优于联邦基线，提供可转移等环境表示。
AI 中文摘要
联邦学习已成为时空预测（STF）的一种有前途的范式，可在不共享原始观测数据的情况下进行协作模型训练。现有联邦STF方法主要将跨客户端异质性视为优化挑战，并通过个性化方法缓解。然而，这种异质性根本源于不同的环境条件，这些方法捕捉特定环境的预测模式，在环境变化时难以泛化。我们的关键见解是利用联邦客户端之间的环境多样性，因为它们提供了对同一潜在时空系统的补充观测。基于此见解，我们提出了\method，一种新颖的联邦去混淆框架，将客户端视为不同的因果环境。\method利用客户端异质性作为分布式环境证据，并学习一个全局原型码本以捕获共享的环境模式。我们进一步推导了一个理论联邦去混淆边界，该边界由平均混淆强度线性控制。大量实验表明，\method始终优于联邦基线，同时提供可转移、可解释且通信高效的环境表示。
英文摘要
Federated learning has emerged as a promising paradigm for spatio-temporal forecasting (STF), enabling collaborative model training without sharing raw observations. Existing federated STF methods primarily regard cross-client heterogeneity as an optimization challenge and mitigate it through personalized approaches. However, such heterogeneity fundamentally stems from diverse \emph{environmental conditions}, and these methods capture environment-specific forecasting patterns, hardly generalizing under environmental shifts. Our key insight is that the environmental diversity across federated clients should be exploited, as they provide \emph{complementary observations of the same underlying spatio-temporal system}. Based on this insight, we propose \method, a novel federated de-confounding framework that \textbf{treats clients as distinct causal environments}. \method leverages the client heterogeneity as distributed environmental evidence and learns a global prototype codebook to capture shared environmental regimes. We further derive a theoretical federated de-confounding bound that is linearly controlled by the averaged confounding strength. Extensive experiments demonstrate that \method consistently outperforms federated baselines, while providing transferable, interpretable, and communication-efficient environmental representations.
