时间序列基础模型的个性化联邦稀疏适配

中文摘要 AI 辅助

时间序列基础模型（TSFMs）的联邦适配因电表数据具有隐私性、分布式特性及高度非独立同分布（non-IID），在构建能源预测领域颇具吸引力。然而，单一参数共享策略难以适配所有预训练TSFMs或建筑客户端：完全共享适配器会抑制建筑特有的时间行为，而完全本地适配则会丢失跨建筑的迁移信息。我们提出一种个性化联邦稀疏适配框架，在预训练TSFM表征后放置异构时间型混合专家（MoE）适配器。序列级路由器将每个168小时的上下文窗口映射到由专家组成的Top-k子集，这些专家分别专注于周期性、长程交互、局部变化、趋势-残差结构及多分辨率行为。我们将该方法与全局联邦学习（FL）、本地训练及个性化FL变体（含全局共享或客户端私有专家库）进行对比。在50栋建筑和3种TSFM主干网络上的实验显示，个性化方法始终优于全局FL-MoE和本地MoE，而最优稀疏适配策略会随主干网络和评估指标变化。路由行为进一步揭示了客户端级别的专家专业化、专家集中度及主干网络间近乎均匀的路由情况，表明联邦TSFM适配需同时兼顾客户端感知和主干网络感知。

英文摘要

Federated adaptation of time-series foundation models (TSFMs) is attractive for building energy forecasting because meter data are private, distributed, and highly non-IID. However, a single parameter-sharing strategy is unlikely to serve all pretrained TSFMs or building clients: fully shared adapters can suppress building-specific temporal behavior, while fully local adaptation discards cross-building transfer. We propose a personalized federated sparse adaptation framework with a heterogeneous temporal mixture-of-experts (MoE) adapter placed after the pretrained TSFM representation. A sequence-level router maps each 168-hour context window to a top-$k$ subset of experts specialized for periodicity, long-range interactions, local variation, trend-residual structure, and multi-resolution behavior. We compare global FL, local training, and personalized FL variants with globally shared or client-private expert banks. Across 50 buildings and three TSFM backbones, personalization consistently outperforms Global FL-MoE and Local MoE, while the best sparse-adaptation strategy varies by backbone and metric. Routing behavior further reveals client-level expert specialization, expert concentration, and near-uniform routing across backbones, showing that federated TSFM adaptation should be both client-aware and backbone-aware.

发表机构

• Robert Bosch Centre for Cyber-Physical Systems, Indian Institute of Science（罗伯特·博世网络物理系统中心，印度科学学院）
• School of Computing, Newcastle University（纽卡斯尔大学计算学院）

机构由 AI 辅助整理，请以论文原文为准。

补充信息

备注

15 pages