CoIFNet: A Unified Framework for Multivariate Time Series Forecasting with Missing Values

TL;DR

CoIFNet is a unified deep learning framework that improves multivariate time series forecasting accuracy and efficiency in the presence of missing data by integrating imputation and forecasting processes.

Contribution

The paper introduces CoIFNet, a novel unified framework that combines imputation and forecasting for robust multivariate time series prediction with missing values, outperforming prior methods.

Findings

Outperforms state-of-the-art methods by up to 24.40% in accuracy.

Improves computational efficiency by over 4 times in memory and 2 times in speed.

Demonstrates robustness across diverse missing-data scenarios.

Abstract

Multivariate time series forecasting (MTSF) is a critical task with broad applications in domains such as meteorology, transportation, and economics. Nevertheless, pervasive missing values caused by sensor failures or human errors significantly degrade forecasting accuracy. Prior efforts usually employ an impute-then-forecast paradigm, leading to suboptimal predictions due to error accumulation and misaligned objectives between the two stages. To address this challenge, we propose the Collaborative Imputation-Forecasting Network (CoIFNet), a novel framework that unifies imputation and forecasting to achieve robust MTSF in the presence of missing values. Specifically, CoIFNet takes the observed values, mask matrix and timestamp embeddings as input, processing them sequentially through the Cross-Timestep Fusion (CTF) and Cross-Variate Fusion (CVF) modules to capture temporal dependencies that are robust to missing values. We provide theoretical justifications on how our CoIFNet learning objective improves the performance bound of MTSF with missing values. Through extensive experiments on challenging MSTF benchmarks, we demonstrate the effectiveness and computational efficiency of our proposed approach across diverse missing-data scenarios, e.g., CoIFNet outperforms the state-of-the-art method by $\underline{\textbf{24.40}}$% ($\underline{\textbf{23.81}}$%) at a point (block) missing rate of 0.6, while improving memory and time efficiency by $\underline{\boldsymbol{4.3\times}}$ and $\underline{\boldsymbol{2.1\times}}$, respectively. Our code is available at: https://github.com/KaiTang-eng/CoIFNet.