Time-FFM: Towards LM-Empowered Federated Foundation Model for Time Series Forecasting

arXiv:2405.14252v1 Announce Type: new
Abstract: Unlike natural language processing and computer vision, the development of Foundation Models (FMs) for time series forecasting is blocked due to data scarcity. While recent efforts are focused on building such FMs by unlocking the potential of language models (LMs) for time series analysis, dedicated parameters for various downstream forecasting tasks need training, which hinders the common knowledge sharing across domains. Moreover, data owners may hesitate to share the access to local data due to …

abstract analysis arxiv building computer computer vision cs.lg data development forecasting foundation foundation model language language models language processing lms natural natural language natural language processing potential processing series time series time series forecasting type vision while