OpenML Benchmarking Suites and the OpenML100

77 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Benchmark and Survey of Automated Machine Learning Frameworks (2019, methodology): “More specifically, a combination of the curated benchmarking suites OpenML1006 (Bischl et al., 2017), OpenML-CC187 (Bischl et al., 2019) and AutoML Benchmark8 (Gijsbers et al., 2019) is used.”
Survey on Automated Machine Learning (2019, methodology): “At first, all previously mentioned CASH algorithms are tested on the complete OpenML100 suite.”
Do Not Trust Additive Explanations (2019, methodology): “We have performed experiment on 28 data sets from OpenML100 (Bischl et al., 2017) collection of data sets.”
Benchmarking Automatic Machine Learning Frameworks (2018, background): “(Bischl et al., 2017) OpenML hosts datasets on their website while exposing an API to access the datasets.”
Tunability: Importance of Hyperparameters of Machine Learning Algorithms (2018, methodology): “Regarding the experimental setup, we compute more hyperparameter runs (around 2.5 million vs. 250000), but consider only the 38 binary classiﬁcation datasets of OpenML100 while van Rijn and Hutter (2017) use all the 100 datasets which also contain multiclass datasets.”
Hyperparameter Importance Across Datasets (2017, methodology): “OpenML also defines curated benchmarking suites, such as the OpenML100 [4].”