{"type":"ScholarlyArticle","title":"Time-Frequency Disentanglement Boosted Pre-Training: A Universal Spatio-Temporal Modeling Framework","authors":[{"name":"Yudong Zhang","slug":"yudong-zhang","given":"Yudong","family":"Zhang","affiliation":""},{"name":"Zhaoyang Sun","slug":"zhaoyang-sun","given":"Zhaoyang","family":"Sun","affiliation":""},{"name":"Xu Wang","slug":"xu-wang","given":"Xu","family":"Wang","affiliation":""},{"name":"Xuan Yu","slug":"xuan-yu","given":"Xuan","family":"Yu","affiliation":""},{"name":"Kai Wang","slug":"kai-wang","given":"Kai","family":"Wang","affiliation":""},{"name":"Yang Wang","slug":"yang-wang","given":"Yang","family":"Wang","affiliation":""}],"abstract":"Current spatio-temporal modeling techniques largely rely on the abundant data and the design of task-specific models. However, many cities lack well-established digital infrastructures, making data scarcity and the high cost of model development significant barriers to application deployment. Therefore, this work aims to enable spatio-temporal learning to cope with the problems of few-shot data modeling and model generalizability. To this end, we propose a Universal Spatio-Temporal Correlationship pre-training framework (USTC), for spatio-temporal modeling across different cities and tasks. To enhance the spatio-temporal representations during pre-training, we propose to decouple the time-frequency patterns within data, and leverage contrastive learning to maintain the time-frequency consistency. To further improve the adaptability to downstream tasks, we design a prompt generation module to mine personalized spatio-temporal patterns on the target city, which can be integrated with the learned common spatio-temporal representations to collaboratively serve downstream tasks. Extensive experiments conducted on real-world datasets demonstrate that USTC significantly outperforms the advanced baselines in forecasting, imputation, and extrapolation across cities.","doi":"10.24963/ijcai.2025/407","url":"https://ijcai.org/proceedings/2025/407","pdf":"https://ijcai.org/proceedings/2025/0407.pdf","markdown":"https://ijcai.org/proceedings/2025/407.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/407","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"Data Mining","track":"Main Track","number":407,"pages":{"first":3660,"last":3669},"keywords":["Data Mining: DM: Mining spatial and/or temporal data","Multidisciplinary Topics and Applications: MTA: Transportation","Machine Learning: ML: Time series and data streams"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}