用自监督填补数据+Mixup增强时序预测，提升模型泛化能力。
IBMA: An Imputation-Based Mixup Augmentation Using Self-Supervised Learning for Time Series Data
- 先自监督填补缺失数据，再用Mixup生成新样本。
- 在4个数据集上24次实验中22次表现更好，10次最优。
- 适合时序预测新手或想提升模型鲁棒性的研究者。
时间序列预测中的数据增强对提升模型性能至关重要，能引入多样性同时保持时间模式。然而，相比图像或文本领域，时序数据的增强策略较少，先进方法如Mixup应用有限。本文提出一种新方法——基于填补的Mixup增强（IBMA），将填补后的数据与Mixup结合，以增强模型泛化能力并提高预测性能。我们在多个前沿预测模型（DLinear、TimesNet、iTrainformer）上验证该方法，涵盖四个数据集（ETTh1、ETTh2、ETTm1、ETTm2），并与八种其他增强技术对比。实验表明，IBMA在24次测试中取得22次性能提升，其中10次为最佳表现，尤其在iTrainformer填补方案下效果显著。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。