Impacts of Data Splitting Strategies on Parameterized Link Prediction Algorithms

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Jiao, Xinshan, Luo, Yuxin, Bi, Yilin, Zhou, Tao
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866918432808632320
author Jiao, Xinshan
Luo, Yuxin
Bi, Yilin
Zhou, Tao
author_facet Jiao, Xinshan
Luo, Yuxin
Bi, Yilin
Zhou, Tao
contents Link prediction is a fundamental problem in network science, aiming to infer potential or missing links based on observed network structures. With the increasing adoption of parameterized models, the rigor of evaluation protocols has become critically important. However, a previously common practice of using the test set during hyperparameter tuning has led to human-induced information leakage, thereby inflating the reported model performance. To address this issue, this study introduces a novel evaluation metric, Loss Ratio, which quantitatively measures the extent of performance overestimation. We conduct large-scale experiments on 60 real-world networks across six domains. The results demonstrate that the information leakage leads to an average overestimation of about 3.6%, with the bias reaching over 15% for specific algorithms. Meanwhile, heuristic and random-walk-based methods exhibit greater robustness and stability. The analysis uncovers a pervasive information leakage issue in link prediction evaluation and underscores the necessity of adopting standardized data splitting strategies to enable fair and reproducible benchmarking of link prediction models.
format Preprint
id arxiv_https___arxiv_org_abs_2511_05834
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Impacts of Data Splitting Strategies on Parameterized Link Prediction Algorithms
Jiao, Xinshan
Luo, Yuxin
Bi, Yilin
Zhou, Tao
Other Statistics
Link prediction is a fundamental problem in network science, aiming to infer potential or missing links based on observed network structures. With the increasing adoption of parameterized models, the rigor of evaluation protocols has become critically important. However, a previously common practice of using the test set during hyperparameter tuning has led to human-induced information leakage, thereby inflating the reported model performance. To address this issue, this study introduces a novel evaluation metric, Loss Ratio, which quantitatively measures the extent of performance overestimation. We conduct large-scale experiments on 60 real-world networks across six domains. The results demonstrate that the information leakage leads to an average overestimation of about 3.6%, with the bias reaching over 15% for specific algorithms. Meanwhile, heuristic and random-walk-based methods exhibit greater robustness and stability. The analysis uncovers a pervasive information leakage issue in link prediction evaluation and underscores the necessity of adopting standardized data splitting strategies to enable fair and reproducible benchmarking of link prediction models.
title Impacts of Data Splitting Strategies on Parameterized Link Prediction Algorithms
topic Other Statistics
url https://arxiv.org/abs/2511.05834