This corpus has been collected from free or free for research sources at the Internet:
6 PAPERS • 1 BENCHMARK
Wild-Time is a benchmark of 5 datasets that reflect temporal distribution shifts arising in a variety of real-world applications, including patient prognosis and news classification. On these datasets, we systematically benchmark 13 prior approaches, including methods in domain generalization, continual learning, self-supervised learning, and ensemble learning.
4 PAPERS • NO BENCHMARKS YET
The model forecasts for the sub-seasonal forecasting application considered in the Online Learning under Optimism and Delay paper experiments. This dataset consists of a single ZIP archive (919MB) that contains 1) a "models" folder that contains, for each model the forecasts for the Precip. 3-4w, Precip. 5-6w, Temp. 3-4w, Temp. 5-6w tasks on the western United States geography, and 2) a "data" folder that contains supporting geographic data. The data should be used to reproduce the PoolD experiments in https://github.com/geflaspohler/poold as described in the README. (2021-06-10)
1 PAPER • NO BENCHMARKS YET