Recurrent Neural Networks for Multivariate Time Series with Missing Values

6 Jun 2016Zhengping CheSanjay PurushothamKyunghyun ChoDavid SontagYan Liu

Multivariate time series data in practical applications, such as health care, geoscience, and biology, are characterized by a variety of missing values. In time series prediction and other related tasks, it has been noted that missing values and their missing patterns are often correlated with the target labels, a.k.a., informative missingness... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Multivariate Time Series Forecasting MuJoCo RNN GRU-D MSE (10^-2, 50% missing) 5.833 # 4
Multivariate Time Series Imputation MuJoCo RNN GRU-D MSE (10^2, 50% missing) 0.748 # 4
Time Series Classification PhysioNet Challenge 2012 RNN GRU-D AUC 81.8% # 7
AUC Stdev 0.8% # 3

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet