Multivariate time series imputation with transformers

Date
2022-11-25
Advisor
Instructor
Source Title
IEEE Signal Processing Letters
Print ISSN
1070-9908
Electronic ISSN
1558-2361
Publisher
IEEE
Volume
29
Issue
Pages
2517 - 2521
Language
English
Type
Article
Journal Title
Journal ISSN
Volume Title
Abstract

Processing time series with missing segments is a fundamental challenge that puts obstacles to advanced analysis in various disciplines such as engineering, medicine, and economics. One of the remedies is imputation to fill the missing values based on observed values properly without undermining performance. We propose the Multivariate Time-Series Imputation with Transformers (MTSIT), a novel method that uses transformer architecture in an unsupervised manner for missing value imputation. Unlike the existing transformer architectures, this model only uses the encoder part of the transformer due to computational benefits. Crucially, MTSIT trains the autoencoder by jointly reconstructing and imputing stochastically-masked inputs via an objective designed for multivariate time-series data. The trained autoencoder is then evaluated for imputing both simulated and real missing values. Experiments show that MTSIT outperforms state-of-the-art imputation methods over benchmark datasets.

Course
Other identifiers
Book Title
Keywords
Transformers, Time series analysis, Training, Decoding, Data models, Medical services, Computational modeling
Citation
Published Version (Please cite this version)