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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Li, Yuqi, Ding, Kuiye, Yang, Chuanguang, Wang, Hao, Wang, Haoxuan, Duan, Huiran, Liu, Junming, Tian, Yingli
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917096421588992
author Li, Yuqi
Ding, Kuiye
Yang, Chuanguang
Wang, Hao
Wang, Haoxuan
Duan, Huiran
Liu, Junming
Tian, Yingli
author_facet Li, Yuqi
Ding, Kuiye
Yang, Chuanguang
Wang, Hao
Wang, Haoxuan
Duan, Huiran
Liu, Junming
Tian, Yingli
contents 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 synthesizing compact datasets that preserve the learning behavior of full data. However, extending dataset distillation to time-series forecasting is non-trivial due to two fundamental challenges: 1.temporal bias from strong autocorrelation, which leads to distorted value-term alignment between teacher and student models; and 2.insufficient diversity among synthetic samples, arising from the absence of explicit categorical priors to regularize trajectory variety. In this work, we propose DDTime, a lightweight and plug-in distillation framework built upon first-order condensation decomposition. To tackle Challenge 1, it revisits value-term alignment through temporal statistics and introduces a frequency-domain alignment mechanism to mitigate autocorrelation-induced bias, ensuring spectral consistency and temporal fidelity. To address Challenge 2, we further design an inter-sample regularization inspired by the information bottleneck principle, which enhances diversity and maximizes information density across synthetic trajectories. The combined objective is theoretically compatible with a wide range of condensation paradigms and supports stable first-order optimization. Extensive experiments on 20 benchmark datasets and diverse forecasting architectures demonstrate that DDTime consistently outperforms existing distillation methods, achieving about 30% relative accuracy gains while introducing about 2.49% computational overhead. All code and distilled datasets will be released.
format Preprint
id arxiv_https___arxiv_org_abs_2511_16715
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DDTime: Dataset Distillation with Spectral Alignment and Information Bottleneck for Time-Series Forecasting
Li, Yuqi
Ding, Kuiye
Yang, Chuanguang
Wang, Hao
Wang, Haoxuan
Duan, Huiran
Liu, Junming
Tian, Yingli
Machine Learning
Artificial Intelligence
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 synthesizing compact datasets that preserve the learning behavior of full data. However, extending dataset distillation to time-series forecasting is non-trivial due to two fundamental challenges: 1.temporal bias from strong autocorrelation, which leads to distorted value-term alignment between teacher and student models; and 2.insufficient diversity among synthetic samples, arising from the absence of explicit categorical priors to regularize trajectory variety. In this work, we propose DDTime, a lightweight and plug-in distillation framework built upon first-order condensation decomposition. To tackle Challenge 1, it revisits value-term alignment through temporal statistics and introduces a frequency-domain alignment mechanism to mitigate autocorrelation-induced bias, ensuring spectral consistency and temporal fidelity. To address Challenge 2, we further design an inter-sample regularization inspired by the information bottleneck principle, which enhances diversity and maximizes information density across synthetic trajectories. The combined objective is theoretically compatible with a wide range of condensation paradigms and supports stable first-order optimization. Extensive experiments on 20 benchmark datasets and diverse forecasting architectures demonstrate that DDTime consistently outperforms existing distillation methods, achieving about 30% relative accuracy gains while introducing about 2.49% computational overhead. All code and distilled datasets will be released.
title DDTime: Dataset Distillation with Spectral Alignment and Information Bottleneck for Time-Series Forecasting
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2511.16715