Keywords: Continuous-time model, Irregularly sampled time series, Electronic health records
Abstract: Continuous-time models such as Neural ODEs and Neural Flows have shown promising results in analyzing irregularly sampled time series frequently encountered in electronic health records. Based on these models, time series are typically processed with a hybrid of an initial value problem (IVP) solver and a recurrent neural network within the variational autoencoder architecture. Sequentially solving IVPs makes such models computationally less efficient. In this paper, we propose to model time series purely with continuous processes whose state evolution can be approximated directly by IVPs. This eliminates the need for recurrent computation and enables multiple states to evolve in parallel. We further fuse the encoder and decoder with one IVP-solver based on its invertibility, which leads to fewer parameters and faster convergence. Experiments on two EHR datasets show that the proposed approach achieves comparable classification performance while gaining more than 10x speedup over other continuous-time counterparts.
Anonymity: We agree to keep the submission (including any supplements and/or code) anonymous.
Formatting: We confirm that we read and complied with the author's instructions.
0 Replies
Loading