On the effect of the average clustering coefficient on topology-based link prediction in featureless graphs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Rafiepour, Mehrdad, Vahidipour, S. Mehdi
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912184381997056
author Rafiepour, Mehrdad
Vahidipour, S. Mehdi
author_facet Rafiepour, Mehrdad
Vahidipour, S. Mehdi
contents Link prediction is a fundamental problem in graph theory with diverse applications, including recommender systems, community detection, and identifying spurious connections. While feature-based methods achieve high accuracy, their reliance on node attributes limits their applicability in featureless graphs. For such graphs, structure-based approaches, including common neighbor-based and degree-dependent methods, are commonly employed. However, the effectiveness of these methods depends on graph density, with common neighbor-based algorithms performing well in dense graphs and degree-dependent methods being more suitable for sparse or tree-like graphs. Despite this, the literature lacks a clear criterion to distinguish between dense and sparse graphs. This paper introduces the average clustering coefficient as a criterion for assessing graph density to assist with the choice of link prediction algorithms. To address the scarcity of datasets for empirical analysis, we propose a novel graph generation method based on the Barabasi-Albert model, which enables controlled variation of graph density while preserving structural heterogeneity. Through comprehensive experiments on synthetic and real-world datasets, we establish an empirical boundary for the average clustering coefficient that facilitates the selection of effective link prediction techniques.
format Preprint
id arxiv_https___arxiv_org_abs_2501_06721
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle On the effect of the average clustering coefficient on topology-based link prediction in featureless graphs
Rafiepour, Mehrdad
Vahidipour, S. Mehdi
Social and Information Networks
05C85
G.2.2
Link prediction is a fundamental problem in graph theory with diverse applications, including recommender systems, community detection, and identifying spurious connections. While feature-based methods achieve high accuracy, their reliance on node attributes limits their applicability in featureless graphs. For such graphs, structure-based approaches, including common neighbor-based and degree-dependent methods, are commonly employed. However, the effectiveness of these methods depends on graph density, with common neighbor-based algorithms performing well in dense graphs and degree-dependent methods being more suitable for sparse or tree-like graphs. Despite this, the literature lacks a clear criterion to distinguish between dense and sparse graphs. This paper introduces the average clustering coefficient as a criterion for assessing graph density to assist with the choice of link prediction algorithms. To address the scarcity of datasets for empirical analysis, we propose a novel graph generation method based on the Barabasi-Albert model, which enables controlled variation of graph density while preserving structural heterogeneity. Through comprehensive experiments on synthetic and real-world datasets, we establish an empirical boundary for the average clustering coefficient that facilitates the selection of effective link prediction techniques.
title On the effect of the average clustering coefficient on topology-based link prediction in featureless graphs
topic Social and Information Networks
05C85
G.2.2
url https://arxiv.org/abs/2501.06721