Salvato in:
Dettagli Bibliografici
Autori principali: Xu, Fan, Wu, Hao, Wang, Kun, Wang, Nan, Wen, Qingsong, Wu, Xian, Gong, Wei, Zhao, Xibin
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2510.24216
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915582588223488
author Xu, Fan
Wu, Hao
Wang, Kun
Wang, Nan
Wen, Qingsong
Wu, Xian
Gong, Wei
Zhao, Xibin
author_facet Xu, Fan
Wu, Hao
Wang, Kun
Wang, Nan
Wen, Qingsong
Wu, Xian
Gong, Wei
Zhao, Xibin
contents In dynamical system modeling, traditional numerical methods are limited by high computational costs, while modern data-driven approaches struggle with data scarcity and distribution shifts. To address these fundamental limitations, we first propose SPARK, a physics-guided quantitative augmentation plugin. Specifically, SPARK utilizes a reconstruction autoencoder to integrate physical parameters into a physics-rich discrete state dictionary. This state dictionary then acts as a structured dictionary of physical states, enabling the creation of new, physically-plausible training samples via principled interpolation in the latent space. Further, for downstream prediction, these augmented representations are seamlessly integrated with a Fourier-enhanced Graph ODE, a combination designed to robustly model the enriched data distribution while capturing long-term temporal dependencies. Extensive experiments on diverse benchmarks demonstrate that SPARK significantly outperforms state-of-the-art baselines, particularly in challenging out-of-distribution scenarios and data-scarce regimes, proving the efficacy of our physics-guided augmentation paradigm.
format Preprint
id arxiv_https___arxiv_org_abs_2510_24216
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Unlocking Out-of-Distribution Generalization in Dynamics through Physics-Guided Augmentation
Xu, Fan
Wu, Hao
Wang, Kun
Wang, Nan
Wen, Qingsong
Wu, Xian
Gong, Wei
Zhao, Xibin
Machine Learning
In dynamical system modeling, traditional numerical methods are limited by high computational costs, while modern data-driven approaches struggle with data scarcity and distribution shifts. To address these fundamental limitations, we first propose SPARK, a physics-guided quantitative augmentation plugin. Specifically, SPARK utilizes a reconstruction autoencoder to integrate physical parameters into a physics-rich discrete state dictionary. This state dictionary then acts as a structured dictionary of physical states, enabling the creation of new, physically-plausible training samples via principled interpolation in the latent space. Further, for downstream prediction, these augmented representations are seamlessly integrated with a Fourier-enhanced Graph ODE, a combination designed to robustly model the enriched data distribution while capturing long-term temporal dependencies. Extensive experiments on diverse benchmarks demonstrate that SPARK significantly outperforms state-of-the-art baselines, particularly in challenging out-of-distribution scenarios and data-scarce regimes, proving the efficacy of our physics-guided augmentation paradigm.
title Unlocking Out-of-Distribution Generalization in Dynamics through Physics-Guided Augmentation
topic Machine Learning
url https://arxiv.org/abs/2510.24216