Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Federated Foundation Models on Heterogeneous Time Series

About

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.

Shengchao Chen, Guodong Long, Jing Jiang, Chengqi Zhang• 2024

Related benchmarks

TaskDatasetResultRank
Time Series ForecastingETTh2
MSE0.395
561
Long-term forecastingETTm1
MSE0.323
375
Long-term forecastingETTh1
MSE0.391
365
Anomaly DetectionSMD
F1 Score89.88
359
Long-term forecastingETTm2
MSE0.179
310
Time Series ForecastingWeather
MSE0.252
295
Anomaly DetectionSWaT
F1 Score91.12
276
Long-term forecastingETTh2
MSE0.334
266
Time Series ForecastingExchange
MSE0.39
199
Time Series ForecastingElectricity
MSE0.187
114
Showing 10 of 37 rows

Other info

Follow for update