{"ID":2864863,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.23494","arxiv_id":"2509.23494","title":"Revisiting Multivariate Time Series Forecasting with Missing Values","abstract":"Missing values are common in real-world time series, and multivariate time series forecasting with missing values (MTSF-M) has become a crucial area of research for ensuring reliable predictions. To address the challenge of missing data, current approaches have developed an imputation-then-prediction framework that uses imputation modules to fill in missing values, followed by forecasting on the imputed data. However, this framework overlooks a critical issue: there is no ground truth for the missing values, making the imputation process susceptible to errors that can degrade prediction accuracy. In this paper, we conduct a systematic empirical study and reveal that imputation without direct supervision can corrupt the underlying data distribution and actively degrade prediction accuracy. To address this, we propose a paradigm shift that moves away from imputation and directly predicts from the partially observed time series. We introduce Consistency-Regularized Information Bottleneck (CRIB), a novel framework built on the Information Bottleneck principle. CRIB combines a unified-variate attention mechanism with a consistency regularization scheme to learn robust representations that filter out noise introduced by missing values while preserving essential predictive signals. Comprehensive experiments on four real-world datasets demonstrate the effectiveness of CRIB, which predicts accurately even under high missing rates. Our code is available in https://github.com/Muyiiiii/CRIB.","short_abstract":"Missing values are common in real-world time series, and multivariate time series forecasting with missing values (MTSF-M) has become a crucial area of research for ensuring reliable predictions. To address the challenge of missing data, current approaches have developed an imputation-then-prediction framework that use...","url_abs":"https://arxiv.org/abs/2509.23494","url_pdf":"https://arxiv.org/pdf/2509.23494v3","authors":"[\"Jie Yang\",\"Yifan Hu\",\"Kexin Zhang\",\"Luyang Niu\",\"Philip S. Yu\",\"Kaize Ding\"]","published":"2025-09-27T20:57:48Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\",\"stat.ML\"]","methods":"[]","has_code":false,"code_links":[{"ID":609208,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2864863,"paper_url":"https://arxiv.org/abs/2509.23494","paper_title":"Revisiting Multivariate Time Series Forecasting with Missing Values","repo_url":"https://github.com/Muyiiiii/CRIB","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}