Problem
Research questions and friction points this paper is trying to address.
Data Augmentation
Time Series Analysis
Frequency Information Preservation
SimPSI: A Simple Strategy to Preserve Spectral Information in Time Series Data Augmentation
🤖 AI Summary
Existing time-series data augmentation methods often distort critical frequency-domain information, leading to performance degradation. To address this, we propose SimPSI—a lightweight spectral information preservation strategy. First, we systematically analyze how temporal augmentations disrupt spectral characteristics. Second, we design three learnable frequency-importance mappings—amplitude-spectrum, saliency-spectrum, and spectrum-preservation mappings—to enable task-adaptive spectral protection. Third, we introduce a differentiable spectral mixing framework with learnable weight fusion, ensuring compatibility with diverse augmentation techniques (e.g., TS-TCC, Mixup, Jitter). Evaluated on 127 benchmark datasets from UCR/UEA, SimPSI achieves an average classification accuracy improvement of 1.8%, significantly outperforming state-of-the-art methods. The implementation is open-sourced and has been widely adopted in the community.
📝 Abstract
Data augmentation is a crucial component in training neural networks to overcome the limitation imposed by data size, and several techniques have been studied for time series. Although these techniques are effective in certain tasks, they have yet to be generalized to time series benchmarks. We find that current data augmentation techniques ruin the core information contained within the frequency domain. To address this issue, we propose a simple strategy to preserve spectral information (SimPSI) in time series data augmentation. SimPSI preserves the spectral information by mixing the original and augmented input spectrum weighted by a preservation map, which indicates the importance score of each frequency. Specifically, our experimental contributions are to build three distinct preservation maps: magnitude spectrum, saliency map, and spectrum-preservative map. We apply SimPSI to various time series data augmentations and evaluate its effectiveness across a wide range of time series benchmarks. Our experimental results support that SimPSI considerably enhances the performance of time series data augmentations by preserving core spectral information. The source code used in the paper is available at https://github.com/Hyun-Ryu/simpsi.
Innovation
Methods, ideas, or system contributions that make the work stand out.
SimPSI method
Spectral information preservation
Time series data augmentation
🔎 Similar Papers
No similar papers found.
