解决时间序列模型的异构数据偏见问题，提升泛化能力。
FeDaL: Federated Dataset Learning for General Time Series Foundation Models
- 用联邦学习分解异构数据，学习通用时间特征
- 在8个任务54个基线中显著优于现有方法
- 适合处理分布式时间序列数据的科研与工业场景
数据集层面的异质性引入了显著的领域偏见，严重削弱了通用时间序列基础模型（TSFMs）的泛化能力，但这一挑战尚未得到充分研究。本文重新思考基于联邦学习范式从零训练TSFMs的方法。提出一种新型联邦数据学习（FeDaL）框架，通过学习数据集无关的时间表征来应对异构时间序列。联邦学习的分布式架构天然将异构时间序列数据分解为共享的通用知识与保留的个性化知识。此外，基于TSFM架构，FeDaL通过两种互补机制——域偏见消除（DBE）与全局偏见消除（GBE），显式缓解局部与全局偏见。在涵盖8类任务（包括回归与分类）的真实世界数据集上，对54个基线进行了广泛评估。进一步分析了联邦扩展行为，揭示了数据量、客户端数量和加入率对去中心化环境下模型性能的影响。代码已公开于 https://github.com/shengchaochen82/FeDaL。
原文摘要 · Abstract (English)
Dataset-level heterogeneity introduces significant domain biases that fundamentally degrade generalization on general Time Series Foundation Models (TSFMs), yet this challenge remains underexplored. This paper rethinks the from-scratch training of TSFMs using the paradigm of federated learning. We propose a novel Federated Dataset Learning (FeDaL) approach to tackle heterogeneous time series by learning dataset-agnostic temporal representations. Specifically, the distributed architecture of federated learning is a nature solution to decompose heterogeneous TS datasets into shared generalized knowledge and preserved personalized knowledge. Moreover, based on the TSFM architecture, FeDaL explicitly mitigates both local and global biases by adding two complementary mechanisms: Domain Bias Elimination (DBE) and Global Bias Elimination (GBE). FeDaL`s cross-dataset generalization has been extensively evaluated in real-world datasets spanning eight tasks (including various regression and classification), against 54 baselines. We further analyze federated scaling behavior, showing how data volume, client count, and join rate affect model performance under decentralization. Our code is publicly available at https://github.com/shengchaochen82/FeDaL
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。