{"type":"ScholarlyArticle","title":"Beyond Uniform Updates: Drift Pattern Aware Online Time Series Forecasting Under Delayed Feedback","authors":[{"name":"Xingwang Li","slug":"xingwang-li","given":"Xingwang","family":"Li","affiliation":""},{"name":"Fei Teng","slug":"fei-teng","given":"Fei","family":"Teng","affiliation":""},{"name":"Cong Zhou","slug":"cong-zhou","given":"Cong","family":"Zhou","affiliation":""},{"name":"Qiang Duan","slug":"qiang-duan","given":"Qiang","family":"Duan","affiliation":""}],"abstract":"Online time series forecasting relies on continual updates to cope with concept drift. In multi-step forecasting, however, the ground truth for an H-step prediction arrives only after H steps, so a delayed residual entangles persistent drifts with transient shocks and seasonal fluctuations. Existing methods typically apply a uniform update rule to all delayed errors, which can overreact to noise and under-adapt to real drift. We view delayed residuals as compressed observations of latent drift over the horizon, and propose PADRE, a drift evidence driven framework that converts each delayed feedback event into a context-sensitive adaptation decision. PADRE builds a Tri-View drift representation from (i) the current input context, (ii) recent delayed-residual trajectories, and (iii) retrieved typical types of drift, and quantifies their agreement via a geometric consistency measure. To exploit recurring drift structure, PADRE mines an offline Pattern Bank of regime-conditioned residual prototypes and retrieves a soft pattern prompt online. A lightweight prompt guided policy outputs a continuous update gate that scales the backbone’s gradient step, enabling decisive updates under coherent evidence and conservative updates otherwise. Experiments on five real-world benchmarks and three backbones demonstrate consistent gains under delayed feedback, reducing MSE by 6%–15% relative to recent baselines and improving update stability across horizons.","doi":"10.24963/ijcai.2026/503","url":"https://ijcai.org/proceedings/2026/503","pdf":"https://ijcai.org/proceedings/2026/0503.pdf","markdown":"https://ijcai.org/proceedings/2026/503.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/503","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":503,"pages":{"first":4518,"last":4526},"keywords":["Machine Learning: Time series and data streams","Machine Learning: Multi-view learning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}