EXIT: Extrapolation and Interpolation-based Neural Controlled Differential Equations for Time-series Classification and Forecasting

Sheo Yon Jhin, Jaehoon Lee, Minju Jo, Seungji Kook, Jinsung Jeon, Jihyeon Hyeong, Jayoung Kim, Noseong Park

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

Deep learning inspired by differential equations is a recent research trend and has marked the state of the art performance for many machine learning tasks. Among them, time-series modeling with neural controlled differential equations (NCDEs) is considered as a breakthrough. In many cases, NCDE-based models not only provide better accuracy than recurrent neural networks (RNNs) but also make it possible to process irregular time-series. In this work, we enhance NCDEs by redesigning their core part, i.e., generating a continuous path from a discrete time-series input. NCDEs typically use interpolation algorithms to convert discrete time-series samples to continuous paths. However, we propose to i) generate another latent continuous path using an encoder-decoder architecture, which corresponds to the interpolation process of NCDEs, i.e., our neural network-based interpolation vs. the existing explicit interpolation, and ii) exploit the generative characteristic of the decoder, i.e., extrapolation beyond the time domain of original data if needed. Therefore, our NCDE design can use both the interpolated and the extrapolated information for downstream machine learning tasks. In our experiments with 5 real-world datasets and 12 baselines, our extrapolation and interpolation-based NCDEs outperform existing baselines by non-trivial margins.

Original languageEnglish
Title of host publicationWWW 2022 - Proceedings of the ACM Web Conference 2022
PublisherAssociation for Computing Machinery, Inc
Pages3102-3112
Number of pages11
ISBN (Electronic)9781450390965
DOIs
Publication statusPublished - 2022 Apr 25
Event31st ACM World Wide Web Conference, WWW 2022 - Virtual, Online, France
Duration: 2022 Apr 252022 Apr 29

Publication series

NameWWW 2022 - Proceedings of the ACM Web Conference 2022

Conference

Conference31st ACM World Wide Web Conference, WWW 2022
Country/TerritoryFrance
CityVirtual, Online
Period22/4/2522/4/29

Bibliographical note

Publisher Copyright:
© 2022 ACM.

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Software

Fingerprint

Dive into the research topics of 'EXIT: Extrapolation and Interpolation-based Neural Controlled Differential Equations for Time-series Classification and Forecasting'. Together they form a unique fingerprint.

Cite this