Time Series Classification On Physionet

Metrics

AUPRC

Results

Performance results of various models on this benchmark

Model Name	AUPRC	Paper Title	Repository
GRU-D - APC (n = 0)	53.3	As easy as APC: overcoming missing data and class imbalance in time series with self-supervised learning
GRU-D [12]	53.7	As easy as APC: overcoming missing data and class imbalance in time series with self-supervised learning
GRU-D - APC (n = 1)	55.1	As easy as APC: overcoming missing data and class imbalance in time series with self-supervised learning
IP-Nets	-	Set Functions for Time Series
ODE-RNN	-	Latent ODEs for Irregularly-Sampled Time Series
Phased-LSTM	-	Set Functions for Time Series
Latent ODE + Poisson	-	Latent ODEs for Irregularly-Sampled Time Series
GRU-APC (n = 0)	50.4	As easy as APC: overcoming missing data and class imbalance in time series with self-supervised learning
GRU-D [4]	-	As easy as APC: overcoming missing data and class imbalance in time series with self-supervised learning
SeFT-Attn	-	Set Functions for Time Series
GRU-Simple	-	Set Functions for Time Series
BRITS [4]	-	As easy as APC: overcoming missing data and class imbalance in time series with self-supervised learning
Transformer	-	Set Functions for Time Series
mTAND-Full	-	Multi-Time Attention Networks for Irregularly Sampled Time Series
GRU-D	-	Recurrent Neural Networks for Multivariate Time Series with Missing Values
GRU-Forward	52	As easy as APC: overcoming missing data and class imbalance in time series with self-supervised learning
Latent ODE (ODE enc	-	Latent ODEs for Irregularly-Sampled Time Series
GRU-Simple	53.8	As easy as APC: overcoming missing data and class imbalance in time series with self-supervised learning
IP-NETS	-	Interpolation-Prediction Networks for Irregularly Sampled Time Series
RNN ∆t	-	-	-

0 of 28 row(s) selected.