Reconstruction of complex network from time series data based on graph attention network and Gumbel Softmax

Zhitao Wang (), Weinuo Jiang (), Wenkai Wu () and Shihong Wang
Additional contact information
Zhitao Wang: School of Sciences, Beijing University of Posts and Telecommunications, Beijing 100876, P. R. China
Weinuo Jiang: School of Sciences, Beijing University of Posts and Telecommunications, Beijing 100876, P. R. China
Wenkai Wu: School of Sciences, Beijing University of Posts and Telecommunications, Beijing 100876, P. R. China
Shihong Wang: School of Sciences, Beijing University of Posts and Telecommunications, Beijing 100876, P. R. China

International Journal of Modern Physics C (IJMPC), 2023, vol. 34, issue 05, 1-15

Abstract: It is a challenging practical problem to infer the network structure from measurable time series data. Recently, with the rapid development of graph deep learning, Zhang et al. [Appl. Netw. Sci. 4, 110 (2019)] applied graph neural network to the field of network reconstruction and proposed Gumbel Graph Network. In this paper, a graph deep learning network reconstruction method based on graph attention network and Gumbel Softmax (GAT-GS) is proposed, which can realize high accuracy network reconstruction and node state prediction of discrete and continuous systems. The GAT-GS model is designed based on the dynamic equation of nodes. It consists of two parts: a network structure learner to reconstruct a more real rather than functionally connected networks, based on Gumbel Softmax sampling to generate network structures; and a node state learner using graph attention networks to learn the state evolution of nodes, with the introduction of Laplacian matrix and adjacency matrix for better adaptation to diffusion coupling and unidirectional coupling systems. This model is trained to dynamically adjust the network adjacency matrix and attention coefficients to obtain the network structure and predict the node state. Experimental results show that the GAT-GS model has high reconstruction accuracy, strong robustness and high universality. It can be applied to various kinds of dynamic systems, including Coupled Map Lattice model and Lorenz system, can deal with time series data from regular to complete chaos, can reconstruct various kinds of complex networks, including regular network, Barabási–Albert network and Watts–Strogatz small world network, and it can also reconstruct networks from small scale to large scale with higher computational efficiency.

Keywords: Complex network; network reconstruction; node state prediction; Gumbel Softmax; graph attention network (search for similar items in EconPapers)
Date: 2023
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.worldscientific.com/doi/abs/10.1142/S0129183123500572
Access to full text is restricted to subscribers

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:wsi:ijmpcx:v:34:y:2023:i:05:n:s0129183123500572

Ordering information: This journal article can be ordered from

DOI: 10.1142/S0129183123500572

Access Statistics for this article

International Journal of Modern Physics C (IJMPC) is currently edited by H. J. Herrmann

More articles in International Journal of Modern Physics C (IJMPC) from World Scientific Publishing Co. Pte. Ltd.
Bibliographic data for series maintained by Tai Tone Lim ().