Revisiting Multivariate Time Series Forecasting with Missing Values

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Jie, Hu, Yifan, Zhang, Kexin, Niu, Luyang, Yu, Philip S., Ding, Kaize
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918316257312768
author Yang, Jie
Hu, Yifan
Zhang, Kexin
Niu, Luyang
Yu, Philip S.
Ding, Kaize
author_facet Yang, Jie
Hu, Yifan
Zhang, Kexin
Niu, Luyang
Yu, Philip S.
Ding, Kaize
contents Missing values are common in real-world time series, and multivariate time series forecasting with missing values (MTSF-M) has become a crucial area of research for ensuring reliable predictions. To address the challenge of missing data, current approaches have developed an imputation-then-prediction framework that uses imputation modules to fill in missing values, followed by forecasting on the imputed data. However, this framework overlooks a critical issue: there is no ground truth for the missing values, making the imputation process susceptible to errors that can degrade prediction accuracy. In this paper, we conduct a systematic empirical study and reveal that imputation without direct supervision can corrupt the underlying data distribution and actively degrade prediction accuracy. To address this, we propose a paradigm shift that moves away from imputation and directly predicts from the partially observed time series. We introduce Consistency-Regularized Information Bottleneck (CRIB), a novel framework built on the Information Bottleneck principle. CRIB combines a unified-variate attention mechanism with a consistency regularization scheme to learn robust representations that filter out noise introduced by missing values while preserving essential predictive signals. Comprehensive experiments on four real-world datasets demonstrate the effectiveness of CRIB, which predicts accurately even under high missing rates. Our code is available in https://github.com/Muyiiiii/CRIB.
format Preprint
id arxiv_https___arxiv_org_abs_2509_23494
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Revisiting Multivariate Time Series Forecasting with Missing Values
Yang, Jie
Hu, Yifan
Zhang, Kexin
Niu, Luyang
Yu, Philip S.
Ding, Kaize
Machine Learning
Artificial Intelligence
Missing values are common in real-world time series, and multivariate time series forecasting with missing values (MTSF-M) has become a crucial area of research for ensuring reliable predictions. To address the challenge of missing data, current approaches have developed an imputation-then-prediction framework that uses imputation modules to fill in missing values, followed by forecasting on the imputed data. However, this framework overlooks a critical issue: there is no ground truth for the missing values, making the imputation process susceptible to errors that can degrade prediction accuracy. In this paper, we conduct a systematic empirical study and reveal that imputation without direct supervision can corrupt the underlying data distribution and actively degrade prediction accuracy. To address this, we propose a paradigm shift that moves away from imputation and directly predicts from the partially observed time series. We introduce Consistency-Regularized Information Bottleneck (CRIB), a novel framework built on the Information Bottleneck principle. CRIB combines a unified-variate attention mechanism with a consistency regularization scheme to learn robust representations that filter out noise introduced by missing values while preserving essential predictive signals. Comprehensive experiments on four real-world datasets demonstrate the effectiveness of CRIB, which predicts accurately even under high missing rates. Our code is available in https://github.com/Muyiiiii/CRIB.
title Revisiting Multivariate Time Series Forecasting with Missing Values
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2509.23494