Important node identification for complex networks based on improved Electre Multi-Attribute fusion

TL;DR

This paper introduces an improved Electre-based multi-attribute decision fusion method, SK-E, for identifying important nodes in complex networks, demonstrating higher accuracy in influence maximization tasks across various models and real networks.

Contribution

The paper proposes a novel SK-E decision fusion method using improved Electre to effectively identify key nodes in complex networks, integrating local and global metrics.

Findings

Superior accuracy over existing methods in node importance identification

Effective across multiple influence spread models

Validated on six real-world networks

Abstract

Influence maximization problem involves selecting a subset of seed nodes within a social network to maximize information spread under a given diffusion model, so how to identify the important nodes is the problem to be considered in this paper. Due to the great differences in the reality of the network, a class of multi-attribute decision fusion methods is often used to solve this problem. Electre is mostly used to solve the problems of investment order, benefit, and risk assessment of projects in economics, which supports the decision maker to make choices by comparing the differences between a set of alternatives. In this paper, we propose a multi-attribute decision fusion method named SK-E, which construct local and global metrics for different networks, use the improved Electre to make decision fusion between local and global metrics of nodes, to get the optimal weight between local and global metrics, and then identify the important nodes. The proposed method demonstrates superior accuracy compared to other methods, as evaluated through three experiments: the SIR epidemic model, the independent cascade model, and constraint efficiency. These experiments were conducted across six different real networks selected as the experimental dataset.