A neural diffusion model for identifying influential nodes in complex networks

Waseem Ahmad and Bang Wang

Chaos, Solitons & Fractals, 2024, vol. 189, issue P1

Abstract: Identifying influential nodes in complex networks through influence diffusion models is a challenging problem that has garnered significant attention in recent years. While many heuristic algorithms have been developed to address this issue, neural models that account for weighted influence remain underexplored. In this paper, we introduce a neural diffusion model (NDM) designed to identify weighted influential nodes in complex networks. Our NDM is trained on small-scale networks and learns to map network structures to the corresponding weighted influence of nodes, leveraging the weighted independent cascade model to provide insights into network dynamics. Specifically, we extract weight-based features from nodes at various scales to capture their local structures. We then employ a neural encoder to incorporate neighborhood information and learn node embeddings by integrating features across different scales into sequential neural units. Finally, a decoding mechanism transforms these node embeddings into estimates of weighted influence. Experimental results on both real-world and synthetic networks demonstrate that our NDM outperforms state-of-the-art techniques, achieving superior prediction performance.

Keywords: Influential nodes; Weighted independent model; Complex networks; Deep learning (search for similar items in EconPapers)
Date: 2024
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0960077924012347
Full text for ScienceDirect subscribers only

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:eee:chsofr:v:189:y:2024:i:p1:s0960077924012347

DOI: 10.1016/j.chaos.2024.115682

Access Statistics for this article

Chaos, Solitons & Fractals is currently edited by Stefano Boccaletti and Stelios Bekiros

More articles in Chaos, Solitons & Fractals from Elsevier
Bibliographic data for series maintained by Thayer, Thomas R. ().