Discriminating abilities of threshold-free evaluation metrics in link prediction

Abstract

Link prediction is a paradigmatic and challenging problem in network science, which attempts to uncover missing links or predict future links, based on known topology. A fundamental but still unsolved issue is how to choose proper metrics to fairly evaluate prediction algorithms. The area under the receiver operating characteristic curve (AUC) and the balanced precision (BP) are the two most popular metrics in early studies, while their effectiveness is recently under debate. At the same time, the area under the precision-recall curve (AUPR) becomes increasingly popular, especially in biological studies. Based on a toy model with tunable noise and predictability, we propose a method to measure the discriminating abilities of any given metric. We apply this method to the above three threshold-free metrics, showing that AUC and AUPR are remarkably more discriminating than BP, and AUC is slightly more discriminating than AUPR. The result suggests that it is better to simultaneously use AUC and AUPR in evaluating link prediction algorithms, at the same time, it warns us that the evaluation based only on BP may be unauthentic. This article provides a starting point towards a comprehensive picture about effectiveness of evaluation metrics for link prediction and other classification problems.

arXiv comment27 pages, 5 figures, 1 table

References in corpus (21)

• Emergence of scaling in random networks
• Link Prediction in Complex Networks: A Survey
• Hierarchical structure and the prediction of missing links in networks
• Predicting Missing Links via Local Information
• How to project a bipartite network?
• Recommender Systems
• Structure and dynamics of molecular networks: A novel paradigm of drug discovery. A comprehensive review
• Missing and spurious interactions and the reconstruction of complex networks
• Generation of uncorrelated random scale-free networks
• Link Prediction Based on Local Random Walk
• Simplicial Closure and higher-order link prediction
• Random graphs with clustering
• Evaluating Link Prediction Methods
• All scale-free networks are sparse
• Stacking Models for Nearly Optimal Link Prediction in Complex Networks
• Progresses and Challenges in Link Prediction
• Link Prediction via Matrix Completion
• Reconstruction methods for networks: the case of economic and financial systems
• Evaluating Network Models: A Likelihood Analysis
• Experimental analyses on 2-hop-based and 3-hop-based link prediction algorithms
• Link prediction with hyperbolic geometry

Cited by in corpus (4)

• The maximum capability of a topological feature in link prediction
• Beyond Pairwise Interactions: Unveiling the Role of Higher-Order Interactions via Stepwise Reduction
• Domain matters: Towards domain-informed evaluation for link prediction
• Impacts of Data Splitting Strategies on Parameterized Link Prediction Algorithms