Rethinking the positive role of cluster structure in complex networks for link prediction tasks

TL;DR

This paper introduces ClusterLP, a clustering-driven framework that leverages cluster structures to improve link prediction accuracy in both undirected and directed complex networks, demonstrating competitive results on real-world data.

Contribution

The paper proposes a novel clustering-based link prediction framework, ClusterLP, tailored for undirected and directed graphs, emphasizing the positive role of cluster structure.

Findings

ClusterLP achieves high accuracy in link prediction tasks.

The framework is effective on multiple real-world network datasets.

ClusterLP outperforms several baseline models.

Abstract

Clustering is a fundamental problem in network analysis that finds closely connected groups of nodes and separates them from other nodes in the graph, while link prediction is to predict whether two nodes in a network are likely to have a link. The definition of both naturally determines that clustering must play a positive role in obtaining accurate link prediction tasks. Yet researchers have long ignored or used inappropriate ways to undermine this positive relationship. In this article, We construct a simple but efficient clustering-driven link prediction framework(ClusterLP), with the goal of directly exploiting the cluster structures to obtain connections between nodes as accurately as possible in both undirected graphs and directed graphs. Specifically, we propose that it is easier to establish links between nodes with similar representation vectors and cluster tendencies in undirected graphs, while nodes in a directed graphs can more easily point to nodes similar to their representation vectors and have greater influence in their own cluster. We customized the implementation of ClusterLP for undirected and directed graphs, respectively, and the experimental results using multiple real-world networks on the link prediction task showed that our models is highly competitive with existing baseline models. The code implementation of ClusterLP and baselines we use are available at https://github.com/ZINUX1998/ClusterLP.