{"ID":3053201,"CreatedAt":"2026-06-04T04:41:36.695875263Z","UpdatedAt":"2026-06-05T18:46:40.353075213Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.04135","arxiv_id":"2606.04135","title":"Stationarity-Aware Retrieval-Augmented Time Series Forecasting","abstract":"Time series forecasting relies on historical patterns, but real-world series often exhibit non-stationarity and regime shifts that challenge fully parametric forecasters. Inspired by Retrieval-Augmented Generation (RAG), recent work augments forecasters by retrieving relevant historical segments and using them as external evidence at inference time. However, due to the intrinsic non-stationarity of real-world time series, a highly similar past segment does not necessarily imply a similar future, rendering similarity-only retrieval brittle and prone to redundancy. We propose Stationarity-Aware Retrieval-Augmented Time Series Forecasting (SARAF), a framework that adaptively balances relevance and diversity in retrieval. SARAF first forms a candidate pool via temporal similarity with time-aligned enhancement, then applies a diversity-aware selection strategy to cover heterogeneous historical regimes, with the diversification strength automatically modulated by dataset-level stationarity. Moreover, SARAF uses stationarity-aware aggregation to fuse the retrieved futures. Extensive experiments on eight real-world datasets show that SARAF achieves competitive forecasting performance and improves average accuracy and robustness over strong baselines, with particularly clear benefits under challenging non-stationary settings. Code: https://github.com/ShiqiaoZhou/SARAF.","short_abstract":"Time series forecasting relies on historical patterns, but real-world series often exhibit non-stationarity and regime shifts that challenge fully parametric forecasters. Inspired by Retrieval-Augmented Generation (RAG), recent work augments forecasters by retrieving relevant historical segments and using them as exter...","url_abs":"https://arxiv.org/abs/2606.04135","url_pdf":"https://arxiv.org/pdf/2606.04135v1","authors":"[\"Shiqiao Zhou\",\"Holger Schöner\",\"Zipeng Wu\",\"Edouard Fouché\",\"IAG Wilson\",\"Shuo Wang\"]","published":"2026-06-02T18:47:16Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[\"RAG\"]","has_code":false,"code_links":[{"ID":612799,"CreatedAt":"2026-06-04T04:41:36.695875263Z","UpdatedAt":"2026-06-04T04:41:36.695875263Z","DeletedAt":null,"paper_id":3053201,"paper_url":"https://arxiv.org/abs/2606.04135","paper_title":"Stationarity-Aware Retrieval-Augmented Time Series Forecasting","repo_url":"https://github.com/ShiqiaoZhou/SARAF","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}