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

• URL: http://arxiv.org/abs/2511.16715v1
• Date: Thu, 20 Nov 2025 16:50:09 GMT
• Title: DDTime: Dataset Distillation with Spectral Alignment and Information Bottleneck for Time-Series Forecasting
• Authors: Yuqi Li, Kuiye Ding, Chuanguang Yang, Hao Wang, Haoxuan Wang, Huiran Duan, Junming Liu, Yingli Tian,
• Abstract summary: Time-series forecasting is fundamental across many domains, yet training accurate models often requires large-scale datasets and computational resources.<n>We propose DDTime, a lightweight and plug-in distillation framework built upon first-order condensation decomposition.<n> DDTime consistently outperforms existing distillation methods, achieving about 30% relative accuracy gains while introducing about 2.49% computational overhead.
• Score: 28.005308500582405
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: 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.

Related papers

• Harmonic Dataset Distillation for Time Series Forecasting [18.325250900037474]
  Time Series forecasting (TSF) in the modern era faces significant computational and storage cost challenges due to the massive scale of real-world data.<n>We propose Harmonic dataset Distillation for Time Series Forecasting (HDT)<n>HDT decomposes the time series into its sinusoidal basis through the FFT and aligns the core periodic structure by Harmonic Matching.
  arXiv  Detail & Related papers  (2026-03-04T06:16:23Z)
• A Unified Frequency Domain Decomposition Framework for Interpretable and Robust Time Series Forecasting [81.73338008264115]
  Current approaches for time series forecasting, whether in the time or frequency domain, predominantly use deep learning models based on linear layers or transformers.<n>We propose FIRE, a unified frequency domain decomposition framework that provides a mathematical abstraction for diverse types of time series.<n>Fire consistently outperforms state-of-the-art models on long-term forecasting benchmarks.
  arXiv  Detail & Related papers  (2025-10-11T09:59:25Z)
• TIMED: Adversarial and Autoregressive Refinement of Diffusion-Based Time Series Generation [0.31498833540989407]
  TIMED is a unified generative framework that captures global structure via a forward-reverse diffusion process.<n>To further align the real and synthetic distributions in feature space, TIMED incorporates a Maximum Mean Discrepancy (MMD) loss.<n>We show that TIMED generates more realistic and temporally coherent sequences than state-of-the-art generative models.
  arXiv  Detail & Related papers  (2025-09-23T23:05:40Z)
• Time-o1: Time-Series Forecasting Needs Transformed Label Alignment [50.54348432664401]
  Time-o1 is a transformation-augmented learning objective tailored for time-series forecasting.<n>The central idea is to transform the label sequence into decorrelated components with discriminated significance.<n>Time-o1 achieves state-of-the-art performance and is compatible with various forecast models.
  arXiv  Detail & Related papers  (2025-05-23T13:00:35Z)
• Spatial-Temporal-Spectral Unified Modeling for Remote Sensing Dense Prediction [20.1863553357121]
  Current deep learning architectures for remote sensing are fundamentally rigid.<n>We introduce the Spatial-Temporal-Spectral Unified Network (STSUN) for unified modeling.<n> STSUN can adapt to input and output data with arbitrary spatial sizes, temporal lengths, and spectral bands.<n>It unifies various dense prediction tasks and diverse semantic class predictions.
  arXiv  Detail & Related papers  (2025-05-18T07:39:17Z)
• TD3: Tucker Decomposition Based Dataset Distillation Method for Sequential Recommendation [50.23504065567638]
  This paper introduces textbfTD3, a novel textbfDataset textbfDistillation method within a meta-learning framework.<n> TD3 distills a fully expressive emphsynthetic sequence summary from original data.<n>An augmentation technique allows the learner to closely fit the synthetic summary, ensuring an accurate update of it in the emphouter-loop.
  arXiv  Detail & Related papers  (2025-02-05T03:13:25Z)
• Enhancing Foundation Models for Time Series Forecasting via Wavelet-based Tokenization [74.3339999119713]
  We develop a wavelet-based tokenizer that allows models to learn complex representations directly in the space of time-localized frequencies.<n>Our method first scales and decomposes the input time series, then thresholds and quantizes the wavelet coefficients, and finally pre-trains an autoregressive model to forecast coefficients for the forecast horizon.
  arXiv  Detail & Related papers  (2024-12-06T18:22:59Z)
• Tackling Data Heterogeneity in Federated Time Series Forecasting [61.021413959988216]
  Time series forecasting plays a critical role in various real-world applications, including energy consumption prediction, disease transmission monitoring, and weather forecasting. Most existing methods rely on a centralized training paradigm, where large amounts of data are collected from distributed devices to a central cloud server. We propose a novel framework, Fed-TREND, to address data heterogeneity by generating informative synthetic data as auxiliary knowledge carriers.
  arXiv  Detail & Related papers  (2024-11-24T04:56:45Z)
• From Incomplete Coarse-Grained to Complete Fine-Grained: A Two-Stage Framework for Spatiotemporal Data Reconstruction [11.18240409124747]
  We introduce a two-stage data inference framework, Diffcon, grounded in the Denoising Diffusion Probabilistic Model (DDPM) We conduct experiments on multiple real-world datasets to demonstrate the superiority of our method.
  arXiv  Detail & Related papers  (2024-10-05T13:16:53Z)
• CondTSF: One-line Plugin of Dataset Condensation for Time Series Forecasting [22.473436770730657]
  The objective of dataset condensation is to ensure that the model trained with the synthetic dataset can perform comparably to the model trained with full datasets. In classification, the synthetic data is considered well-distilled if the model trained with the full dataset and the model trained with the synthetic dataset yield identical labels for the same input. In TS-forecasting, the effectiveness of synthetic data distillation is determined by the distance between predictions of the two models.
  arXiv  Detail & Related papers  (2024-06-04T09:18:20Z)
• Dataset Condensation for Time Series Classification via Dual Domain Matching [12.317728375957717]
  We propose a novel framework named dataset textittextbfCondensation for textittextbfTime textittextbfSeries textittextbfClassification via Dual Domain Matching. Our proposed framework aims to generate a condensed dataset that matches the surrogate objectives in both the time and frequency domains.
  arXiv  Detail & Related papers  (2024-03-12T02:05:06Z)
• Generative Time Series Forecasting with Diffusion, Denoise, and Disentanglement [51.55157852647306]
  Time series forecasting has been a widely explored task of great importance in many applications. It is common that real-world time series data are recorded in a short time period, which results in a big gap between the deep model and the limited and noisy time series. We propose to address the time series forecasting problem with generative modeling and propose a bidirectional variational auto-encoder equipped with diffusion, denoise, and disentanglement.
  arXiv  Detail & Related papers  (2023-01-08T12:20:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.