Adaptively-Halting RNN for Tunable Early Time Series Classification
Early time series classification is the task of predicting the class label of a time series before it is observed in its entirety. In time-sensitive domains where information is collected over time, it is worth sacrificing some classification accuracy in favor of earlier predictions, ideally early enough for actions to be taken. However, since accuracy and earliness are contradictory objectives, a solution to this problem must find a task-dependent trade-off. We design the first early classification model called EARLIEST to tackle this multi-objective optimization problem, jointly learning (1) to decide at which time step to halt and generate predictions, and (2) how to classify the time series based on the task and data features. We achieve a user-controlled balance between the goals of earliness and accuracy by pairing a recurrent neural network that learns to classify time series as a supervised learning task with a stochastic controller network that learns a halting-policy as a reinforcement-learning task. The halting-policy dictates sequential decisions, one per time step, of whether or not to halt the recurrent neural network and classify the time series early. This pairing of networks optimizes a global objective function that incorporates both earliness and accuracy. We validate our method via critical clinical prediction tasks in the MIMIC III database from the Beth Israel Deaconess Medical Center along with another publicly available time series classification dataset.
Advisor: Elke Rundensteiner, Ph.D.
Co-Advisor: Xiangnan Kong, Ph.D.
Reader: Randy Paffenroth, Ph.D.