Complex Network Analytics for Structural–Functional Decoding of Neural Networks
Applied Sciences · 01.08.2025 · 15 (15) · 8576
DOI: 10.3390/app15158576 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 01.08.2025. Verfasst von Jiarui Zhang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Neural networks (NNs) achieve breakthroughs in computer vision and natural language processing, yet their “black box” nature persists. Traditional methods prioritise parameter optimisation and loss design, overlooking NNs’ fundamental structure as topologically organised nonlinear computational systems. This work proposes a complex network theory framework decoding structure–function coupling by mapping convolutional layers, fully connected layers, and Dropout modules into graph representations. To overcome limitations of heuristic compression techniques, we develop a topology-sensitive adaptive pruning algorithm that evaluates critical paths via node strength centrality, preserving structural–functional integrity. On CIFAR-10, our method achieves 55.5% parameter reduction with only 7.8% accuracy degradation—significantly outperforming traditional approaches. Crucially, retrained pruned networks exceed original model accuracy by up to 2.63%, demonstrating that topology optimisation unlocks latent model potential. This research establishes a paradigm shift from empirical to topologically rationalised neural architecture design, providing theoretical foundations for deep learning optimisation dynamics.
Zitieren
APA
Zhang, J., Zhang, D., Lou, H., Li, Y., Du, T., & Gao, Y. (2025). Complex Network Analytics for Structural–Functional Decoding of Neural Networks. Applied Sciences, 15(15), 8576. https://doi.org/10.3390/app15158576
Vancouver
Zhang J, Zhang D, Lou H, Li Y, Du T, Gao Y. Complex Network Analytics for Structural–Functional Decoding of Neural Networks. Applied Sciences. 2025;15(15):8576. doi:10.3390/app15158576
BibTeX
@article{Zhang2025,
author = {Zhang, Jiarui and Zhang, Dongxiao and Lou, Hu and Li, Yueer and Du, Taijiao and Gao, Yinjun},
title = {Complex Network Analytics for Structural–Functional Decoding of Neural Networks},
journal = {Applied Sciences},
year = {2025},
volume = {15},
number = {15},
pages = {8576},
doi = {10.3390/app15158576}
}
EUVIMED