IBMA: An Imputation-Based Mixup Augmentation Using Self-Supervised Learning for Time Series Data
This addresses the problem of improving time series forecasting accuracy for researchers and practitioners, though it is incremental as it builds on existing Mixup and imputation techniques.
The paper tackles the limited data augmentation strategies for time series forecasting by proposing IBMA, which combines imputation-augmented data with Mixup augmentation, and shows it consistently enhances performance, achieving 22 improvements out of 24 instances across various models and datasets.
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.