Rethinking Irregular Time Series Forecasting: A Simple yet Effective Baseline

TL;DR

This paper introduces a simple yet effective baseline for irregular time series forecasting using the APN framework, which transforms irregular data into regularized representations and employs a shallow MLP for predictions, outperforming existing methods.

Contribution

The paper proposes a novel APN framework with the TAPA module for adaptive patching, offering a practical and efficient approach to irregular time series forecasting.

Findings

APN outperforms state-of-the-art methods in accuracy.

APN is more efficient in computation.

The TAPA module effectively handles irregularity and missing data.

Abstract

The forecasting of irregular multivariate time series (IMTS) is crucial in key areas such as healthcare, biomechanics, climate science, and astronomy. However, achieving accurate and practical predictions is challenging due to two main factors. First, the inherent irregularity and data missingness in irregular time series make modeling difficult. Second, most existing methods are typically complex and resource-intensive. In this study, we propose a general framework called APN to address these challenges. Specifically, we design a novel Time-Aware Patch Aggregation (TAPA) module that achieves adaptive patching. By learning dynamically adjustable patch boundaries and a time-aware weighted averaging strategy, TAPA transforms the original irregular sequences into high-quality, regularized representations in a channel-independent manner. Additionally, we use a simple query module to effectively integrate historical information while maintaining the model's efficiency. Finally, predictions are made by a shallow MLP. Experimental results on multiple real-world datasets show that APN outperforms existing state-of-the-art methods in both efficiency and accuracy.