Federated Foundation Models on Heterogeneous Time Series

• URL: http://arxiv.org/abs/2412.08906v1
• Date: Thu, 12 Dec 2024 03:38:01 GMT
• Title: Federated Foundation Models on Heterogeneous Time Series
• Authors: Shengchao Chen, Guodong Long, Jing Jiang, Chengqi Zhang,
• Abstract summary: Efforts are primarily focused on fusing cross-domain time series datasets to extract shared subsequences as tokens for training models on Transformer architecture. This paper proposes a novel federated learning approach to address the heterogeneity in time series foundation models training, namely FFTS. The newly learned time series foundation models achieve superior generalization capabilities on cross-domain time series analysis tasks, including forecasting, imputation, and anomaly detection.
• Score: 36.229082478423585
• License:
• Abstract: Training a general-purpose time series foundation models with robust generalization capabilities across diverse applications from scratch is still an open challenge. Efforts are primarily focused on fusing cross-domain time series datasets to extract shared subsequences as tokens for training models on Transformer architecture. However, due to significant statistical heterogeneity across domains, this cross-domain fusing approach doesn't work effectively as the same as fusing texts and images. To tackle this challenge, this paper proposes a novel federated learning approach to address the heterogeneity in time series foundation models training, namely FFTS. Specifically, each data-holding organization is treated as an independent client in a collaborative learning framework with federated settings, and then many client-specific local models will be trained to preserve the unique characteristics per dataset. Moreover, a new regularization mechanism will be applied to both client-side and server-side, thus to align the shared knowledge across heterogeneous datasets from different domains. Extensive experiments on benchmark datasets demonstrate the effectiveness of the proposed federated learning approach. The newly learned time series foundation models achieve superior generalization capabilities on cross-domain time series analysis tasks, including forecasting, imputation, and anomaly detection.

Related papers

• Learning Latent Spaces for Domain Generalization in Time Series Forecasting [60.29403194508811]
  Time series forecasting is vital in many real-world applications, yet developing models that generalize well on unseen relevant domains remains underexplored. We propose a framework for domain generalization in time series forecasting by mining the latent factors that govern temporal dependencies across domains. Our approach uses a decomposition-based architecture with a new Conditional $beta$-Variational Autoencoder (VAE), wherein time series data is first decomposed into trend-cyclical and seasonal components.
  arXiv  Detail & Related papers  (2024-12-15T12:41:53Z)
• 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. We introduce a federated learning approach for estimating the structure of a Dynamic Bayesian Network from homogeneous time series data. 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)
• 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)
• Towards Generalisable Time Series Understanding Across Domains [10.350643783811174]
  We introduce a novel pre-training paradigm specifically designed to handle time series heterogeneity. We propose a tokeniser with learnable domain signatures, a dual masking strategy, and a normalised cross-correlation loss. Our code and pre-trained weights are available at https://www.oetu.com/oetu/otis.
  arXiv  Detail & Related papers  (2024-10-09T17:09:30Z)
• PeFAD: A Parameter-Efficient Federated Framework for Time Series Anomaly Detection [51.20479454379662]
  We propose a. Federated Anomaly Detection framework named PeFAD with the increasing privacy concerns. We conduct extensive evaluations on four real datasets, where PeFAD outperforms existing state-of-the-art baselines by up to 28.74%.
  arXiv  Detail & Related papers  (2024-06-04T13:51:08Z)
• NuwaTS: a Foundation Model Mending Every Incomplete Time Series [24.768755438620666]
  We present textbfNuwaTS, a novel framework that repurposes Pre-trained Language Models for general time series imputation. NuwaTS can be applied to impute missing data across any domain. We show that NuwaTS generalizes to other time series tasks, such as forecasting.
  arXiv  Detail & Related papers  (2024-05-24T07:59:02Z)
• UniCL: A Universal Contrastive Learning Framework for Large Time Series Models [18.005358506435847]
  Time-series analysis plays a pivotal role across a range of critical applications, from finance to healthcare. Traditional supervised learning methods first annotate extensive labels for time-series data in each task. This paper introduces UniCL, a universal and scalable contrastive learning framework designed for pretraining time-series foundation models.
  arXiv  Detail & Related papers  (2024-05-17T07:47:11Z)
• 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)
• UniTime: A Language-Empowered Unified Model for Cross-Domain Time Series Forecasting [59.11817101030137]
  This research advocates for a unified model paradigm that transcends domain boundaries. Learning an effective cross-domain model presents the following challenges. We propose UniTime for effective cross-domain time series learning.
  arXiv  Detail & Related papers  (2023-10-15T06:30:22Z)
• 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)
• Distilling Universal and Joint Knowledge for Cross-Domain Model Compression on Time Series Data [18.41222232863567]
  We propose a novel end-to-end framework called Universal and joint knowledge distillation (UNI-KD) for cross-domain model compression. In particular, we propose to transfer both the universal feature-level knowledge across source and target domains and the joint logit-level knowledge shared by both domains from the teacher to the student model via an adversarial learning scheme.
  arXiv  Detail & Related papers  (2023-07-07T01:48:02Z)

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.