{"type":"ScholarlyArticle","title":"Active Arbitration: Decoupling Spatio-Temporal Duality for Efficient Traffic Forecasting","authors":[{"name":"JiaJun Yu","slug":"jiajun-yu","given":"Jiajun","family":"Yu","affiliation":""},{"name":"Fang Yuan","slug":"fang-yuan","given":"Fang","family":"Yuan","affiliation":""},{"name":"Guang-Yong Chen","slug":"guang-yong-chen","given":"Guang-Yong","family":"Chen","affiliation":""},{"name":"Min Gan","slug":"min-gan","given":"Min","family":"Gan","affiliation":""}],"abstract":"Spatio-temporal forecasting is inherently bottlenecked by a phenomenon we term Spatio-Temporal Duality: the paradoxical coexistence of time-varying physical lags and instantaneous semantic synchrony. Constrained by passive coupling, existing architectures often employ indiscriminate spatial aggregation that fails to dynamically arbitrate interaction intensity based on traffic states, forcing models to rely on redundant deep stacking to approximate complex dynamics. We address this issue by introducing Time Arbitrated Spatial GNN (TAS-GNN), an efficient framework that arbitrates spatial interactions through time. Our model leverages deep temporal semantics to dynamically and proactively manage the aggregation of spatial domains, effectively decoupling physical connectivity from semantic relevance. In addition, to ensure model simplicity, we also introduce spectral decoupling via discrete wavelet Transform (DWT) to capture multiscale dependencies with minimal overhead. Experiments on three real-world datasets (PEMS04, 07, 08) show that TAS-GNN not only outperforms the current baseline model in accuracy, but also significantly improves the inference speed while reducing the number of parameters.","doi":"10.24963/ijcai.2026/583","url":"https://ijcai.org/proceedings/2026/583","pdf":"https://ijcai.org/proceedings/2026/0583.pdf","markdown":"https://ijcai.org/proceedings/2026/583.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/583","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":583,"pages":{"first":5236,"last":5244},"keywords":["Machine Learning: Time series and data streams","Machine Learning: Geometric learning","Machine Learning: Sequence and graph learning","Machine Learning: Attention models"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}