Improved Batching Strategy For Irregular Time-Series ODE
This work addresses a computational bottleneck for researchers and practitioners modeling irregular time-series data, representing an incremental improvement.
The paper tackles the high computational cost of ODE-RNN models for irregular time-series data by proposing an improved batching strategy, resulting in runtime reductions of 2 to 49 times while maintaining comparable accuracy.
Irregular time series data are prevalent in the real world and are challenging to model with a simple recurrent neural network (RNN). Hence, a model that combines the use of ordinary differential equations (ODE) and RNN was proposed (ODE-RNN) to model irregular time series with higher accuracy, but it suffers from high computational costs. In this paper, we propose an improvement in the runtime on ODE-RNNs by using a different efficient batching strategy. Our experiments show that the new models reduce the runtime of ODE-RNN significantly ranging from 2 times up to 49 times depending on the irregularity of the data while maintaining comparable accuracy. Hence, our model can scale favorably for modeling larger irregular data sets.