{"ID":2874016,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.05779","arxiv_id":"2509.05779","title":"Select, then Balance: Exploring Exogenous Variable Modeling of Spatio-Temporal Forecasting","abstract":"Spatio-temporal (ST) forecasting is critical for dynamic systems, yet existing methods predominantly rely on modeling a limited set of observed target variables. In this paper, we present the first systematic exploration of exogenous variable modeling for ST forecasting, a topic long overlooked in this field. We identify two core challenges in integrating exogenous variables: the inconsistent effects of distinct variables on the target system and the imbalance effects between historical and future data. To address these, we propose ExoST, a simple yet effective exogenous variable modeling general framework highly compatible with existing ST backbones that follows a \"select, then balance\" paradigm. Specifically, we design a latent space gated expert module to dynamically select and recompose salient signals from fused exogenous information. Furthermore, a siamese dual-branch backbone architecture captures dynamic patterns from the recomposed past and future representations, integrating them via a context-aware weighting mechanism to ensure dynamic balance. Extensive experiments on real-world datasets demonstrate the ExoST's effectiveness, universality, robustness, and efficiency.","short_abstract":"Spatio-temporal (ST) forecasting is critical for dynamic systems, yet existing methods predominantly rely on modeling a limited set of observed target variables. In this paper, we present the first systematic exploration of exogenous variable modeling for ST forecasting, a topic long overlooked in this field. We identi...","url_abs":"https://arxiv.org/abs/2509.05779","url_pdf":"https://arxiv.org/pdf/2509.05779v3","authors":"[\"Wei Chen\",\"Yuqian Wu\",\"Yuanshao Zhu\",\"Xixuan Hao\",\"Shiyu Wang\",\"Xiaofang Zhou\",\"Yuxuan Liang\"]","published":"2025-09-06T17:22:33Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[\"LoRA\"]","has_code":false}