Abstract
Time series forecasting models often benefit from historical patterns. Inspired by Retrieval-Augmented Generation (RAG), recent research explored retrieving relevant historical time series segments to enhance forecasting. However, relying solely on time series similarity is often insufficient for retrieval under non-stationarity. To address this, we propose a multimodal approach: the
Semantics- Enhanced Retrieval- Augmented Forecasting (SERAF) framework. Unlike mainstream approaches that depend solely on time series similarity, SERAF conducts dual retrieval over the time series and their self-generated textual descriptions. It retrieves two complementary sets of historical patterns and corresponding futures, which are selectively and jointly used to guide future predictions.
Experiments across seven real-world datasets demonstrate the effectiveness of SERAF in bridging numerical and semantic views of time series compared with state-of-the-art baselines.
Blogger's Review: The SERAF framework significantly enhances time series forecasting by integrating numerical data with semantic descriptions, showcasing the potential of multimodal approaches in addressing complex data challenges. This research offers new perspectives and insights for future time series analysis.