Tackling Data Heterogeneity in Federated Time Series Forecasting

TL;DR

This paper introduces Fed-TREND, a federated learning framework that addresses data heterogeneity in time series forecasting by generating synthetic data to improve model consensus and global model refinement.

Contribution

Fed-TREND proposes a novel synthetic data generation approach to enhance federated time series forecasting under data heterogeneity conditions.

Findings

Fed-TREND improves forecasting accuracy across multiple datasets.

Synthetic data enhances model consensus and global refinement.

Framework is compatible with various models and federated setups.

Abstract

Time series forecasting plays a critical role in various real-world applications, including energy consumption prediction, disease transmission monitoring, and weather forecasting. Although substantial progress has been made in time series forecasting, most existing methods rely on a centralized training paradigm, where large amounts of data are collected from distributed devices (e.g., sensors, wearables) to a central cloud server. However, this paradigm has overloaded communication networks and raised privacy concerns. Federated learning, a popular privacy-preserving technique, enables collaborative model training across distributed data sources. However, directly applying federated learning to time series forecasting often yields suboptimal results, as time series data generated by different devices are inherently heterogeneous. In this paper, we propose a novel framework, Fed-TREND, to address data heterogeneity by generating informative synthetic data as auxiliary knowledge carriers. Specifically, Fed-TREND generates two types of synthetic data. The first type of synthetic data captures the representative distribution information from clients' uploaded model updates and enhances clients' local training consensus. The second kind of synthetic data extracts long-term influence insights from global model update trajectories and is used to refine the global model after aggregation. Fed-TREND is compatible with most time series forecasting models and can be seamlessly integrated into existing federated learning frameworks to improve prediction performance. Extensive experiments on eight datasets, using several federated learning baselines and four popular time series forecasting models, demonstrate the effectiveness and generalizability of Fed-TREND.