GRU-D

Reported on 3 benchmarks across 3 tasks · 2 papers

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Time Series2 results

Time Series ClassificationonPhysioNet Challenge 2012
AUPRC· 2021-06-29
53.1
best: 55.1 (GRU-D - APC (n = 1))
As easy as APC: overcoming missing data and class imbalance in time series with self-supervised learning arXiv:2106.15577
Time Series AnalysisonPhysioNet Challenge 2012
F1· 2021-06-29
22.5
best: 87.47 (naive classifier)
As easy as APC: overcoming missing data and class imbalance in time series with self-supervised learning arXiv:2106.15577

Medical1 result

Length-of-Stay predictiononMIMIC-III
Accuracy (LOS>7 Days)· 2019-07-19
91.2
best: 92.3 (Random Forests (RF))
MIMIC-Extract: A Data Extraction, Preprocessing, and Representation Pipeline for MIMIC-III arXiv:1907.08322