Two-Stage Aggregation with Dynamic Local Attention for Irregular Time Series

arXiv:2311.07744v2 Announce Type: replace
Abstract: Irregular multivariate time series data is characterized by varying time intervals between consecutive observations of measured variables/signals (i.e., features) and varying sampling rates (i.e., recordings/measurement) across these features. Modeling time series while taking into account these irregularities is still a challenging task for machine learning methods. Here, we introduce TADA, a Two-stageAggregation process with Dynamic local Attention to harmonize time-wise and feature-wise irregularities in multivariate time series. In the first stage, the irregular time series …

abstract aggregation arxiv attention cs.cy cs.lg data dynamic features local attention machine machine learning measurement modeling multivariate sampling series stage time series type variables while