FeDaL: Federated Dataset Learning for Time Series Foundation Models

• URL: http://arxiv.org/abs/2508.04045v1
• Date: Wed, 06 Aug 2025 03:14:31 GMT
• Title: FeDaL: Federated Dataset Learning for Time Series Foundation Models
• Authors: Shengchao Chen, Guodong Long, Jing Jiang,
• Abstract summary: We propose a novel Federated dataset Learning (FeDaL) approach to tackle heterogeneous time series.<n>FeDaL explicitly mitigates both local and global biases by adding two complementary mechanisms: Domain Bias Elimination (DBE) and Global Bias Elimination (GBE)<n>We show how data volume, client count, and join rate affect model performance under decentralization.
• Score: 28.259753002652793
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Dataset-wise heterogeneity introduces significant domain biases that fundamentally degrade generalization on Time Series Foundation Models (TSFMs), yet this challenge remains underexplored. This paper rethink the development 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 both representation learning and downstream time series analysis, against 54 baselines. We further analyze federated scaling behavior, showing how data volume, client count, and join rate affect model performance under decentralization.

Related papers

• Federated Learning of Dynamic Bayesian Network via Continuous Optimization from Time Series Data [2.4305626489408465]
  In real-world scenarios, data are often distributed across multiple entities that seek to collaboratively learn a Dynamic Bayesian Network.<n>We introduce a federated learning approach for estimating the structure of a Dynamic Bayesian Network from homogeneous time series data.<n>We then extend this approach to heterogeneous time series data by incorporating a proximal operator as a regularization term in a personalized federated learning framework.
  arXiv  Detail & Related papers  (2024-12-13T03:09:35Z)
• Federated Foundation Models on Heterogeneous Time Series [36.229082478423585]
  Efforts are primarily focused on fusing cross-domain time series datasets to extract shared subsequences as tokens for training models on Transformer architecture.<n>This paper proposes a novel federated learning approach to address the heterogeneity in time series foundation models training, namely FFTS.<n>The newly learned time series foundation models achieve superior generalization capabilities on cross-domain time series analysis tasks, including forecasting, imputation, and anomaly detection.
  arXiv  Detail & Related papers  (2024-12-12T03:38:01Z)
• Tackling Data Heterogeneity in Federated Time Series Forecasting [61.021413959988216]
  Time series forecasting plays a critical role in various real-world applications, including energy consumption prediction, disease transmission monitoring, and weather forecasting. Most existing methods rely on a centralized training paradigm, where large amounts of data are collected from distributed devices to a central cloud server. We propose a novel framework, Fed-TREND, to address data heterogeneity by generating informative synthetic data as auxiliary knowledge carriers.
  arXiv  Detail & Related papers  (2024-11-24T04:56:45Z)
• Cross-Dataset Gaze Estimation by Evidential Inter-intra Fusion [38.93368421481945]
  We propose a novel Evidential Inter-intra Fusion EIF framework for training a cross-dataset model.<n>We build independent single-dataset branches for various datasets.<n>We further create a cross-dataset branch to integrate the generalizable features from single-dataset branches.
  arXiv  Detail & Related papers  (2024-09-07T08:53:17Z)
• Improved Generalization Bounds for Communication Efficient Federated Learning [4.3707341422218215]
  This paper focuses on reducing the communication cost of federated learning by exploring generalization bounds and representation learning. We design a novel Federated Learning with Adaptive Local Steps (FedALS) algorithm based on our generalization bound and representation learning analysis.
  arXiv  Detail & Related papers  (2024-04-17T21:17:48Z)
• Federated Learning with Projected Trajectory Regularization [65.6266768678291]
  Federated learning enables joint training of machine learning models from distributed clients without sharing their local data. One key challenge in federated learning is to handle non-identically distributed data across the clients. We propose a novel federated learning framework with projected trajectory regularization (FedPTR) for tackling the data issue.
  arXiv  Detail & Related papers  (2023-12-22T02:12:08Z)
• Fake It Till Make It: Federated Learning with Consensus-Oriented Generation [52.82176415223988]
  We propose federated learning with consensus-oriented generation (FedCOG) FedCOG consists of two key components at the client side: complementary data generation and knowledge-distillation-based model training. Experiments on classical and real-world FL datasets show that FedCOG consistently outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-12-10T18:49:59Z)
• Tackling Computational Heterogeneity in FL: A Few Theoretical Insights [68.8204255655161]
  We introduce and analyse a novel aggregation framework that allows for formalizing and tackling computational heterogeneous data. Proposed aggregation algorithms are extensively analyzed from a theoretical, and an experimental prospective.
  arXiv  Detail & Related papers  (2023-07-12T16:28:21Z)
• FedSiam-DA: Dual-aggregated Federated Learning via Siamese Network under Non-IID Data [21.95009868875851]
  Federated learning can address data island, it remains challenging to train with data heterogeneous in a real application. We propose FedSiam-DA, a novel dual-aggregated contrastive federated learning approach.
  arXiv  Detail & Related papers  (2022-11-17T09:05:25Z)
• Towards Understanding and Mitigating Dimensional Collapse in Heterogeneous Federated Learning [112.69497636932955]
  Federated learning aims to train models across different clients without the sharing of data for privacy considerations. We study how data heterogeneity affects the representations of the globally aggregated models. We propose sc FedDecorr, a novel method that can effectively mitigate dimensional collapse in federated learning.
  arXiv  Detail & Related papers  (2022-10-01T09:04:17Z)
• DRFLM: Distributionally Robust Federated Learning with Inter-client Noise via Local Mixup [58.894901088797376]
  federated learning has emerged as a promising approach for training a global model using data from multiple organizations without leaking their raw data. We propose a general framework to solve the above two challenges simultaneously. We provide comprehensive theoretical analysis including robustness analysis, convergence analysis, and generalization ability.
  arXiv  Detail & Related papers  (2022-04-16T08:08:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.