GRU-ODE-Bayes: Continuous modeling of sporadically-observed time series
This addresses the challenge of irregularly sampled time series for domains like healthcare and climate forecasting, representing an incremental improvement with a novel hybrid method.
The authors tackled the problem of modeling sporadically-observed multidimensional time series, such as clinical patient data, by proposing GRU-ODE-Bayes, which outperformed state-of-the-art methods on synthetic and real-world data in healthcare and climate forecast applications.
Modeling real-world multidimensional time series can be particularly challenging when these are sporadically observed (i.e., sampling is irregular both in time and across dimensions)-such as in the case of clinical patient data. To address these challenges, we propose (1) a continuous-time version of the Gated Recurrent Unit, building upon the recent Neural Ordinary Differential Equations (Chen et al., 2018), and (2) a Bayesian update network that processes the sporadic observations. We bring these two ideas together in our GRU-ODE-Bayes method. We then demonstrate that the proposed method encodes a continuity prior for the latent process and that it can exactly represent the Fokker-Planck dynamics of complex processes driven by a multidimensional stochastic differential equation. Additionally, empirical evaluation shows that our method outperforms the state of the art on both synthetic data and real-world data with applications in healthcare and climate forecast. What is more, the continuity prior is shown to be well suited for low number of samples settings.