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

2025-11-11 · Dang Nha Nguyen, Hai Dang Nguyen, Khoa Tho Anh Nguyen arxiv

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.

📄 PDF Abstract BibTeX arXiv:2511.07930

Code (0)

등록된 구현이 없습니다.

Tasks

Self-Supervised Learning Time Series Forecasting Data Augmentation

Improving Discriminative Visual Representation Learning via Automatic Mixup

2021-09-29 · Siyuan Li, Zicheng Liu, Di wu, Stan Z. Li

Mixup, a convex interpolation technique for data augmentation, has achieved great success in deep neural networks. However, the community usually confines it to supervised scenarios or applies it as a predefined augmenta…

Data Augmentation Representation Learning

Contrastive Mixup: Self- and Semi-Supervised learning for Tabular Domain

2021-08-27 · Sajad Darabi, Shayan Fazeli, Ali Pazoki, Sriram Sankararaman 외

Recent literature in self-supervised has demonstrated significant progress in closing the gap between supervised and unsupervised methods in the image and text domains. These methods rely on domain-specific augmentations…

Exploring Data Augmentations on Self-/Semi-/Fully- Supervised Pre-trained Models

2023-10-28 · Shentong Mo, Zhun Sun, Chao Li

Data augmentation has become a standard component of vision pre-trained models to capture the invariance between augmented views. In practice, augmentation techniques that mask regions of a sample with zero/mean values o…

Data Augmentation Diversity image-classification Image Classification+4

OpenMixup: Open Mixup Toolbox and Benchmark for Visual Representation Learning

2022-09-11 · Siyuan Li, Zedong Wang, Zicheng Liu, Juanxi Tian 외

Mixup augmentation has emerged as a widely used technique for improving the generalization ability of deep neural networks (DNNs). However, the lack of standardized implementations and benchmarks has impeded recent progr…

Benchmarking Classification Image Classification Representation Learning+2

Self-Supervision Improves Diffusion Models for Tabular Data Imputation

2024-07-25 · Yixin Liu, Thalaiyasingam Ajanthan, Hisham Husain, Vu Nguyen

The ubiquity of missing data has sparked considerable attention and focus on tabular data imputation methods. Diffusion models, recognized as the cutting-edge technique for data generation, demonstrate significant potent…

Data Augmentation Diversity Imputation Sensitivity