联邦时间序列基础模型的离散原型记忆
Discrete Prototypical Memories for Federated Time Series Foundation Models
AI总结：
本文提出FeDPM框架，通过离散原型记忆解决联邦学习中时间序列数据与文本空间语义不匹配的问题，提升模型泛化能力与效率。
摘要：
利用大型语言模型（LLMs）作为联邦学习（FL）基于时间序列的基础模型，为将LLMs的泛化能力转移到时间序列数据并保护隐私数据访问提供了有前景的方法。然而，现有LLMs的文本中心潜在空间与时间序列数据之间的语义不一致常导致性能下降。同时，现有FL方法的参数共享机制将异构跨域时间序列数据建模为统一的连续潜在空间，这与时间序列语义通常表现为离散和重复的制度的事实相矛盾。为解决这些限制，我们提出FeDPM，一种基于离散原型记忆的联邦时间序列基础模型框架。具体而言，我们为同一领域的时间序列数据学习局部原型记忆先验。然后对跨域记忆进行对齐，以促进统一的离散潜在空间，并引入领域特定的记忆更新机制以平衡共享和个性化原型知识。广泛实验表明FeDPM的高效性和有效性。代码可在https://anonymous.4open.science/r/FedUnit-64D1公开获取。
英文摘要：
Leveraging Large Language Models (LLMs) as federated learning (FL)-based time series foundation models offers a promising way to transfer the generalization capabilities of LLMs to time series data while preserving access to private data. However, the semantic misalignment between time-series data and the text-centric latent space of existing LLMs often leads to degraded performance. Meanwhile, the parameter-sharing mechanism in existing FL methods model heterogeneous cross-domain time-series data into a unified continuous latent space, which contradicts the fact that time-series semantics frequently manifest as discrete and recurring regimes. To address these limitations, we propose \textsc{FeDPM}, a federated framework for time-series foundation models based on discrete prototypical memories. Specifically, we learn local prototypical memory priors for intra-domain time-series data. We then align cross-domain memories to promote a unified discrete latent space and introduce a domain-specific memory update mechanism to balance shared and personalized prototypical knowledge. Extensive experiments demonstrate the efficiency and effectiveness of \textsc{FeDPM}. The code is publicly available at https://anonymous.4open.science/r/FedUnit-64D1.
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。
