A Unified Framework for Rank-based Evaluation Metrics for Link Prediction in Knowledge Graphs

2022/03/14 by Charles Tapley Hoyt, Hoyt, Charles Tapley, Max Berrendorf +7 · 2 citations
Computer Science · Physics and Astronomy · #Advanced Graph Neural Networks #Artificial Intelligence (cs.AI) #Bayesian Modeling and Causal Inference #Complex Network Analysis Techniques #FOS: Computer and information sciences #Graph Theory and Algorithms #Machine Learning (cs.LG)

paper · pdf · doi:10.48550/arxiv.2203.07544

openalex publication_date 2022/03/14 · openalex created_date 2022/04/03 · openalex updated_date 2026/07/28

Abstract

A presentation of "A Unified Framework for Rank-based Evaluation Metrics for Link Prediction in Knowledge Graphs" (https://arxiv.org/abs/2203.07544) given at GLB2022. More information at: Implementation: https://github.com/pykeen/pykeen Code and analysis: https://github.com/pykeen/ranking-metrics-manuscript Website: https://pykeen.github.io/ranking-metrics-manuscript

Cited by

• How Sharp and Bias-Robust is a Model? Dual Evaluation Perspectives on Knowledge Graph Completion
• Enabling Down Syndrome Research through a Knowledge Graph-Driven Analytical Framework

Related

• Are We Wasting Time? A Fast, Accurate Performance Evaluation Framework for Knowledge Graph Link Predictors
• Evaluating Knowledge Graph Complexity via Semantic, Spectral, and Structural Metrics for Link Prediction
• Inconsistency among evaluation metrics in link prediction
• Inconsistency of evaluation metrics in link prediction
• Global and local evaluation of link prediction tasks with neural\n embeddings