Harmonic Dataset Distillation for Time Series Forecasting

2026-03-04 · Seungha Hong, Sanghwan Jang, Wonbin Kweon, Suyeon Kim, Gyuseok Lee, Hwanjo Yu arxiv

Time Series forecasting (TSF) in the modern era faces significant computational and storage cost challenges due to the massive scale of real-world data. Dataset Distillation (DD), a paradigm that synthesizes a small, compact dataset to achieve training performance comparable to that of the original dataset, has emerged as a promising solution. However, conventional DD methods are not tailored for time series and suffer from architectural overfitting and limited scalability. To address these issues, we propose Harmonic Dataset Distillation for Time Series Forecasting (HDT). HDT decomposes the time series into its sinusoidal basis through the FFT and aligns the core periodic structure by Harmonic Matching. Since this process operates in the frequency domain, all updates during distillation are applied globally without disrupting temporal dependencies of time series. Extensive experiments demonstrate that HDT achieves strong cross-architecture generalization and scalability, validating its practicality for large-scale, real-world applications.

📄 PDF Abstract BibTeX arXiv:2603.03760

Code (0)

등록된 구현이 없습니다.

Tasks

Time Series Forecasting

Effective Dataset Distillation for Spatio-Temporal Forecasting with Bi-dimensional Compression

2026-03-11 · Taehyung Kwon, Yeonje Choi, Yeongho Kim, Kijung Shin arxiv

Spatio-temporal time series are widely used in real-world applications, including traffic prediction and weather forecasting. They are sequences of observations over extensive periods and multiple locations, naturally re…

Time Series Forecasting Time Series Analysis Weather Forecasting Traffic Prediction

T-LLM: Teaching Large Language Models to Forecast Time Series via Temporal Distillation

2026-02-02 · Suhan Guo, Bingxu Wang, Shaodan Zhang, Furao Shen arxiv

Time series forecasting plays a critical role in decision-making across many real-world applications. Unlike data in vision and language domains, time series data is inherently tied to the evolution of underlying process…

Time Series Forecasting

DDTime: Dataset Distillation with Spectral Alignment and Information Bottleneck for Time-Series Forecasting

2025-11-20 · Yuqi Li, Kuiye Ding, Chuanguang Yang, Hao Wang 외 arxiv

Time-series forecasting is fundamental across many domains, yet training accurate models often requires large-scale datasets and substantial computational resources. Dataset distillation offers a promising alternative by…

MFRS: A Multi-Frequency Reference Series Approach to Scalable and Accurate Time-Series Forecasting

2025-03-11 · Liang Yu, Lai Tu, Xiang Bai

Multivariate time-series forecasting holds immense value across diverse applications, requiring methods to effectively capture complex temporal and inter-variable dynamics. A key challenge lies in uncovering the intrinsi…

Multivariate Time Series Forecasting Time Series Time Series Forecasting

Distilling Time Series Foundation Models for Efficient Forecasting

2026-01-19 · Yuqi Li, Kuiye Ding, Chuanguang Yang, Szu-Yu Chen 외 arxiv

Time Series foundation models (TSFMs) deliver strong forecasting performance through large-scale pretraining, but their large parameter sizes make deployment costly. While knowledge distillation offers a natural and effe…

Time Series Forecasting Knowledge Distillation Model Compression