{"type":"ScholarlyArticle","title":"EVENTTSF: Event-Aware Non-Stationary Time Series Forecasting","authors":[{"name":"Yunfeng Ge","slug":"yunfeng-ge","given":"Yunfeng","family":"Ge","affiliation":""},{"name":"Ming Jin","slug":"ming-jin","given":"Ming","family":"Jin","affiliation":""},{"name":"Yiji Zhao","slug":"yiji-zhao","given":"Yiji","family":"Zhao","affiliation":""},{"name":"Hongyan Li","slug":"hongyan-li","given":"Hongyan","family":"Li","affiliation":""},{"name":"Bo Du","slug":"bo-du","given":"Bo","family":"Du","affiliation":""},{"name":"Chang Xu","slug":"chang-xu","given":"Chang","family":"Xu","affiliation":""},{"name":"Shirui Pan","slug":"shirui-pan","given":"Shirui","family":"Pan","affiliation":""}],"abstract":"Time series forecasting is vital in diverse sectors such as energy and transportation, where non-stationary dynamics are deeply intertwined with external events in other modalities such as texts. However, incorporating natural language-based external events to improve non-stationary forecasting remains largely unexplored, as most approaches still rely on a single modality, resulting in limited contextual knowledge and model underperformance. Enabling fine-grained multimodal interactions between temporal and textual data is challenged by two fundamental issues: (1) the gap in modeling interactions among discrete external events and continuous time series in a unified framework; (2) classical uniform diffusion timestep ignores event-induced non-stationary variability, leading to imbalanced denoising difficulty across diffusion stages. In this work, we propose event-aware non-stationary time series forecasting EventTSF, an autoregressive diffusion framework that integrates historical time series and textual events via step-wise diffusion. To mitigate the imbalanced denoising difficulty of uniform timestep sampling, EventTSF uses an event-aware flow-matching timestep conditioned on event semantics. Extensive experiments on 7 synthetic and real-world datasets show that EventTSF outperforms 12 non-stationary time series forecasting baselines, achieving average gains of 41.3% in probabilistic forecasting and 27.5% in deterministic forecasting across all evaluation metrics.","doi":"10.24963/ijcai.2026/480","url":"https://ijcai.org/proceedings/2026/480","pdf":"https://ijcai.org/proceedings/2026/0480.pdf","markdown":"https://ijcai.org/proceedings/2026/480.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/480","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"Machine Learning","track":"Main Track","number":480,"pages":{"first":4313,"last":4321},"keywords":["Machine Learning: Time series and data streams"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}