Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhang, Jiu, Du, Zhanwei, Hu, Hongwei, Wu, Ke, Li, Tongchao, Shi, Chuan, Huang, Xiaohui, Moreno, Yamir, Hu, Yanqing
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2512.08209
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909950686527488
author Zhang, Jiu
Du, Zhanwei
Hu, Hongwei
Wu, Ke
Li, Tongchao
Shi, Chuan
Huang, Xiaohui
Moreno, Yamir
Hu, Yanqing
author_facet Zhang, Jiu
Du, Zhanwei
Hu, Hongwei
Wu, Ke
Li, Tongchao
Shi, Chuan
Huang, Xiaohui
Moreno, Yamir
Hu, Yanqing
contents The dynamical evolution of complex networks underpins the structure-function relationships in natural and artificial systems. Yet, restoring a network's formation from a single static snapshot remains challenging. Here, we present a transferable machine learning framework that infers network evolutionary trajectories solely from present topology. By integrating graph neural networks with transformers, our approach unlocks a latent temporal dimension directly from the static topology. Evaluated across diverse domains, the framework achieves high transfer accuracy of up to 95.3%, demonstrating its robustness and transferability. Applied to the Drosophila brain connectome, it restores the formation times of over 2.6 million neural connections, revealing that early-forming links support essential behaviors such as mating and foraging, whereas later-forming connections underpin complex sensory and social functions. These results demonstrate that a substantial fraction of evolutionary information is encoded within static network architecture, offering a powerful, general tool for elucidating the hidden temporal dynamics of complex systems.
format Preprint
id arxiv_https___arxiv_org_abs_2512_08209
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Restoring Network Evolution from Static Structure
Zhang, Jiu
Du, Zhanwei
Hu, Hongwei
Wu, Ke
Li, Tongchao
Shi, Chuan
Huang, Xiaohui
Moreno, Yamir
Hu, Yanqing
Physics and Society
The dynamical evolution of complex networks underpins the structure-function relationships in natural and artificial systems. Yet, restoring a network's formation from a single static snapshot remains challenging. Here, we present a transferable machine learning framework that infers network evolutionary trajectories solely from present topology. By integrating graph neural networks with transformers, our approach unlocks a latent temporal dimension directly from the static topology. Evaluated across diverse domains, the framework achieves high transfer accuracy of up to 95.3%, demonstrating its robustness and transferability. Applied to the Drosophila brain connectome, it restores the formation times of over 2.6 million neural connections, revealing that early-forming links support essential behaviors such as mating and foraging, whereas later-forming connections underpin complex sensory and social functions. These results demonstrate that a substantial fraction of evolutionary information is encoded within static network architecture, offering a powerful, general tool for elucidating the hidden temporal dynamics of complex systems.
title Restoring Network Evolution from Static Structure
topic Physics and Society
url https://arxiv.org/abs/2512.08209