IBMA: An Imputation-Based Mixup Augmentation Using Self-Supervised Learning for Time Series Data

TL;DR

This paper introduces IBMA, a novel data augmentation method combining imputation and Mixup for time series forecasting, significantly improving model accuracy across multiple datasets and models.

Contribution

The paper presents a new augmentation technique, IBMA, specifically designed for time series data, integrating imputation with Mixup to enhance forecasting performance.

Findings

IBMA outperforms eight other augmentation methods in 22 out of 24 cases.

IBMA achieves the best results in 10 instances, especially with iTrainformer.

Experimental results show consistent performance improvements across datasets and models.

Abstract

Data augmentation in time series forecasting plays a crucial role in enhancing model performance by introducing variability while maintaining the underlying temporal patterns. However, time series data offers fewer augmentation strategies compared to fields such as image or text, with advanced techniques like Mixup rarely being used. In this work, we propose a novel approach, Imputation-Based Mixup Augmentation (IBMA), which combines Imputation-Augmented data with Mixup augmentation to bolster model generalization and improve forecasting performance. We evaluate the effectiveness of this method across several forecasting models, including DLinear (MLP), TimesNet (CNN), and iTrainformer (Transformer), these models represent some of the most recent advances in time series forecasting. Our experiments, conducted on four datasets (ETTh1, ETTh2, ETTm1, ETTm2) and compared against eight other augmentation techniques, demonstrate that IBMA consistently enhances performance, achieving 22 improvements out of 24 instances, with 10 of those being the best performances, particularly with iTrainformer imputation.