Reproduce “VaryST: Generalizable Spatio-Temporal Forecasting Beyond the Closed-World Setting” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Shengnan Guo, Jinjun Cheng, Xiaowei Mao, Jianhao Zhang, Haochen Lv, Yang Jiang, YiHeng Huang, Yan Lin and 2 more
VaryST forecasts traffic across time, sensor-network, and observation-availability shifts by rebuilding target-specific context from current long-term histories. It encodes nodes from histories and retrieves relevant support nodes for each target. On PEMSD3-Stream, training on 2011 and testing without updates on 2012–2017 yields average MAE 10.49, versus 13.01 for STOP; this benchmark does not guarantee performance in every environment.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.