LIFE: Learning Individual Features for Multivariate Time Series Prediction with Missing Values

TL;DR

LIFE introduces a novel framework for multivariate time series prediction with missing data, leveraging correlated features to improve reliability and accuracy over existing methods.

Contribution

The paper proposes the LIFE framework that uses correlated dimensions as auxiliary information to generate more reliable features for MTS prediction with missing values.

Findings

LIFE outperforms state-of-the-art models on real-world datasets.

LIFE effectively suppresses interference from uncorrelated missing data.

The approach improves prediction accuracy in multivariate time series with missing values.

Abstract

Multivariate time series (MTS) prediction is ubiquitous in real-world fields, but MTS data often contains missing values. In recent years, there has been an increasing interest in using end-to-end models to handle MTS with missing values. To generate features for prediction, existing methods either merge all input dimensions of MTS or tackle each input dimension independently. However, both approaches are hard to perform well because the former usually produce many unreliable features and the latter lacks correlated information. In this paper, we propose a Learning Individual Features (LIFE) framework, which provides a new paradigm for MTS prediction with missing values. LIFE generates reliable features for prediction by using the correlated dimensions as auxiliary information and suppressing the interference from uncorrelated dimensions with missing values. Experiments on three real-world data sets verify the superiority of LIFE to existing state-of-the-art models.