Graph-Guided Network for Irregularly Sampled Multivariate Time Series
This addresses the challenge of analyzing time series with irregular sampling and varying sensor observations in domains like healthcare, offering a novel method for improved classification and interpretation.
The paper tackles the problem of irregularly sampled multivariate time series by introducing RAINDROP, a graph neural network that learns sensor dynamics and dependencies, achieving up to 11.4% absolute F1-score improvement over state-of-the-art methods on healthcare and human activity datasets.
In many domains, including healthcare, biology, and climate science, time series are irregularly sampled with varying time intervals between successive readouts and different subsets of variables (sensors) observed at different time points. Here, we introduce RAINDROP, a graph neural network that embeds irregularly sampled and multivariate time series while also learning the dynamics of sensors purely from observational data. RAINDROP represents every sample as a separate sensor graph and models time-varying dependencies between sensors with a novel message passing operator. It estimates the latent sensor graph structure and leverages the structure together with nearby observations to predict misaligned readouts. This model can be interpreted as a graph neural network that sends messages over graphs that are optimized for capturing time-varying dependencies among sensors. We use RAINDROP to classify time series and interpret temporal dynamics on three healthcare and human activity datasets. RAINDROP outperforms state-of-the-art methods by up to 11.4% (absolute F1-score points), including techniques that deal with irregular sampling using fixed discretization and set functions. RAINDROP shows superiority in diverse setups, including challenging leave-sensor-out settings.