Lehr- und Forschungseinheit für Datenbanksysteme

Breadcrumb Navigation


Accepted paper at GLB@WWW 2022

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



Charles Tapley Hoyt, Max Berrendorf, Mikhail Gaklin, Volker Tresp, Benjamin M. Gyori



Workshop on Graph Learning Benchmarks (GLB 2022) at the International World Wide Web Conference (WWW 2022),
26 April 2021, Virtual


The link prediction task on knowledge graphs without explicit negative triples in the training data motivates the usage of rank-based metrics. Here, we review existing rank-based metrics and propose desiderata for improved metrics to address lack of interpretability and comparability of existing metrics to datasets of different sizes and properties. We introduce a simple theoretical framework for rank-based metrics upon which we investigate two avenues for improvements to existing metrics via alternative aggregation functions and concepts from probability theory. We finally propose several new rank-based metrics that are more easily interpreted and compared accompanied by a demonstration of their usage in a benchmarking of knowledge graph embedding models.

Paper available at arXiv.