Skip to yearly menu bar Skip to main content

Workshop: The Symbiosis of Deep Learning and Differential Equations -- III

Unifying Neural Controlled Differential Equations and Neural Flow for Irregular Time Series Classification

YongKyung Oh · Dongyoung Lim · SUNGIL KIM

Keywords: [ Irregular Time Series Classification ] [ neural ordinary differential equations ] [ Neural controlled differential equations ] [ Neural Flows ]


Real-world time series data frequently exhibits irregular sampling intervals and may contain missing values, posing challenges for effective analysis and modeling. To handle these complexities, we present a groundbreaking approach that synergistically combines Neural Controlled Differential Equations (Neural CDEs) with Neural Flows. Central to our methodology is the introduction of a dual latent space, meticulously designed to discern and stabilize latent values amidst the irregularities intrinsic to the sampled time series data. Our empirical investigations span across 18 datasets, encompassing three distinct domains, and tested under four different missing rate scenarios. The findings consistently underscore the superiority of our proposed model over existing benchmarks in the classification of irregularly-sampled time series data. Such robust performance accentuates our model's versatility, making it a promising candidate for the real-world applications.

Chat is not available.