IMNE: Maximizing influence through deep learning-based node embedding in social network

Influence Maximization (IM) is a critical problem in social network analysis and marketing. It involves identifying a subset of nodes in a social network whose activation or influence can lead to the maximal spread of information, ideas, or behaviors within the network. Although many approaches have...

Full description

Bibliographic Details
Published in:Swarm and Evolutionary Computation
Main Author: Hu Q.; Jiang J.; Xu H.; Kassim M.
Format: Article
Language:English
Published: Elsevier B.V. 2024
Online Access:https://www.scopus.com/inward/record.uri?eid=2-s2.0-85193444633&doi=10.1016%2fj.swevo.2024.101609&partnerID=40&md5=e57f43278a0dbb914917346e9b731f21
id 2-s2.0-85193444633
spelling 2-s2.0-85193444633
Hu Q.; Jiang J.; Xu H.; Kassim M.
IMNE: Maximizing influence through deep learning-based node embedding in social network
2024
Swarm and Evolutionary Computation
88

10.1016/j.swevo.2024.101609
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85193444633&doi=10.1016%2fj.swevo.2024.101609&partnerID=40&md5=e57f43278a0dbb914917346e9b731f21
Influence Maximization (IM) is a critical problem in social network analysis and marketing. It involves identifying a subset of nodes in a social network whose activation or influence can lead to the maximal spread of information, ideas, or behaviors within the network. Although many approaches have been developed in the literature to deal with this problem, most of these approaches are ineffective in dealing with large-scale social networks due to free parameters and computational complexity. Embeddings are used to learn low-dimensional representations of nodes in a social network. These embeddings capture the structural and semantic information of nodes and their relationships within the network. By training deep learning models on graph-structured data, node embeddings can capture complex patterns and dependencies in social networks, enabling more effective downstream tasks such as IM. Accordingly, this paper proposes an efficient algorithm to address the IM problem in social networks using deep learning-based Node Embedding (IMNE), which includes shell decomposition, graph/node embedding, and search space reduction as well as the use of local structural features. Our approach combines the power of deep learning for representation learning with the rich structural information present in social networks to address the challenge of IM in complex and dynamic social networks. IMNE uses the Independent Cascade (IC) information diffusion model to determine the labels needed to train the model by calculating the influence of nodes. Experimental results on several real-world networks considering different performance metrics show that IMNE performs better compared to existing baseline and state-of-the-art methods. © 2024 Elsevier B.V.
Elsevier B.V.
22106502
English
Article

author Hu Q.; Jiang J.; Xu H.; Kassim M.
spellingShingle Hu Q.; Jiang J.; Xu H.; Kassim M.
IMNE: Maximizing influence through deep learning-based node embedding in social network
author_facet Hu Q.; Jiang J.; Xu H.; Kassim M.
author_sort Hu Q.; Jiang J.; Xu H.; Kassim M.
title IMNE: Maximizing influence through deep learning-based node embedding in social network
title_short IMNE: Maximizing influence through deep learning-based node embedding in social network
title_full IMNE: Maximizing influence through deep learning-based node embedding in social network
title_fullStr IMNE: Maximizing influence through deep learning-based node embedding in social network
title_full_unstemmed IMNE: Maximizing influence through deep learning-based node embedding in social network
title_sort IMNE: Maximizing influence through deep learning-based node embedding in social network
publishDate 2024
container_title Swarm and Evolutionary Computation
container_volume 88
container_issue
doi_str_mv 10.1016/j.swevo.2024.101609
url https://www.scopus.com/inward/record.uri?eid=2-s2.0-85193444633&doi=10.1016%2fj.swevo.2024.101609&partnerID=40&md5=e57f43278a0dbb914917346e9b731f21
description Influence Maximization (IM) is a critical problem in social network analysis and marketing. It involves identifying a subset of nodes in a social network whose activation or influence can lead to the maximal spread of information, ideas, or behaviors within the network. Although many approaches have been developed in the literature to deal with this problem, most of these approaches are ineffective in dealing with large-scale social networks due to free parameters and computational complexity. Embeddings are used to learn low-dimensional representations of nodes in a social network. These embeddings capture the structural and semantic information of nodes and their relationships within the network. By training deep learning models on graph-structured data, node embeddings can capture complex patterns and dependencies in social networks, enabling more effective downstream tasks such as IM. Accordingly, this paper proposes an efficient algorithm to address the IM problem in social networks using deep learning-based Node Embedding (IMNE), which includes shell decomposition, graph/node embedding, and search space reduction as well as the use of local structural features. Our approach combines the power of deep learning for representation learning with the rich structural information present in social networks to address the challenge of IM in complex and dynamic social networks. IMNE uses the Independent Cascade (IC) information diffusion model to determine the labels needed to train the model by calculating the influence of nodes. Experimental results on several real-world networks considering different performance metrics show that IMNE performs better compared to existing baseline and state-of-the-art methods. © 2024 Elsevier B.V.
publisher Elsevier B.V.
issn 22106502
language English
format Article
accesstype
record_format scopus
collection Scopus
_version_ 1809677880941084672