Improving link prediction in complex networks by adaptively exploiting multiple structural features of networks

TL;DR

This paper introduces an adaptive fusion model that combines multiple structural features for link prediction in complex networks, improving accuracy by tailoring feature contributions to each network's unique structure.

Contribution

The paper proposes a novel adaptive logistic model that dynamically weights multiple structural features for more accurate link prediction across diverse networks.

Findings

The adaptive model outperforms traditional similarity indices.

Structural features vary significantly across networks.

Dynamic weighting improves prediction accuracy.

Abstract

So far, many network-structure-based link prediction methods have been proposed. However, these methods only highlight one or two structural features of networks, and then use the methods to predict missing links in different networks. The performances of these existing methods are not always satisfied in all cases since each network has its unique underlying structural features. In this paper, by analyzing different real networks, we find that the structural features of different networks are remarkably different. In particular, even in the same network, their inner structural features are utterly different. Therefore, more structural features should be considered. However, owing to the remarkably different structural features, the contributions of different features are hard to be given in advance. Inspired by these facts, an \emph{adaptive} fusion model regarding link prediction is proposed to incorporate multiple structural features. In the model, a logistic function combing multiple structural features is defined, then the weight of each feature in the logistic function is \emph{adaptively} determined by exploiting the known structure information. Last, we use the "learnt" logistic function to predict the connection probabilities of missing links. According to our experimental results, we find that the performance of our adaptive fusion model is better than many similarity indices.