Link Prediction Accuracy on Real-World Networks Under Non-Uniform Missing Edge Patterns

TL;DR

This study evaluates how different missing-edge patterns in real-world networks affect the accuracy of various link prediction algorithms, highlighting the importance of considering data collection biases.

Contribution

It systematically analyzes the impact of non-uniform missing-edge patterns on link prediction accuracy across multiple algorithms and datasets, providing practical guidance for algorithm selection.

Findings

Performance varies significantly with missing-edge patterns

Certain algorithms are more robust to non-uniform missing data

Guidelines for choosing link prediction methods based on data collection biases

Abstract

Real-world network datasets are typically obtained in ways that fail to capture all edges. The patterns of missing data are often non-uniform as they reflect biases and other shortcomings of different data collection methods. Nevertheless, uniform missing data is a common assumption made when no additional information is available about the underlying missing-edge pattern, and link prediction methods are frequently tested against uniformly missing edges. To investigate the impact of different missing-edge patterns on link prediction accuracy, we employ 9 link prediction algorithms from 4 different families to analyze 20 different missing-edge patterns that we categorize into 5 groups. Our comparative simulation study, spanning 250 real-world network datasets from 6 different domains, provides a detailed picture of the significant variations in the performance of different link prediction algorithms in these different settings. With this study, we aim to provide a guide for future researchers to help them select a link prediction algorithm that is well suited to their sampled network data, considering the data collection process and application domain.