Influence maximization in social networks based on long-term and short-term interest fusion reverse influence sampling
1月 1, 2026·,,,,,,·
0 分钟阅读时长
Shuxin Yang
Xiao Fang
Guixiang Zhu
Jian Huang
Fumin Ma
Youquan Wang
Zhendong Wang
摘要
With the rapid development of online social networks, identifying the most
influential user groups and designating them as source nodes for information dissemination
has attracted increasing attention, as this approach can help maximize information
dissemination efficiency. In particular, Influence Maximization (IM) in multi-entity
social networks becomes a very hot topic recently. However, existing methodologies
confront two critical limitations: first, most studies fail to adequately account
for the fact that the correlations between the target item and other items can change
with users’ evolving interests, thus oversimplifying the complex relationships between
items. Second, an unresolved trade-off between computational efficiency and algorithmic
precision, thereby restricting their scalability in large-scale network applications.
To address these challenges, this paper proposes a Long-term and Short-term interest
Fusion-based Reverse Influence Sampling model (named LSF-RIS) for the issue of multi-entity
IM. LSF-RIS consists of two main components: (1) a Deep Longterm and Short-term
interest Fusion (DLSF) module that dynamically models user preferences through temporal
interest integration, thereby enhancing the prediction accuracy of user activation
probabilities for target items; and (2) a Weighted Core Decomposition-enhanced Reverse
Influence Sampling (RIS-WCD) mechanism, which optimizes the network topology by
pruning non-critical nodes, retains the core nodes and crucial connections within
the network, and thereby achieves enhanced computational efficiency without compromising
sampling accuracy. Extensive experiments on three public social network datasets
demonstrate the superiority of LSF-RIS over state-of-the-art methods, as evidenced
by metrics of both accuracy and computational efficiency.
类型
出版物
Engineering Applications of Artificial Intelligence