Home | Publications | BFV+20b

Interpretable and Fair Comparison of Link Prediction or Entity Alignment Methods With Adjusted Mean Rank (Extended Abstract)

MCML Authors

Max Berrendorf

Dr.

* Former Member

→ Group Volker Tresp
Database Systems, Data Mining and AI

Evgeny Faerman

Dr.

* Former Member

→ Group Matthias Schubert
Spatial Artificial Intelligence

Volker Tresp

Prof. Dr.

Principal Investigator

Database Systems, Data Mining and AI

Abstract

In this work, we take a closer look at the evaluation of two families of methods for enriching information from knowledge graphs: Link Prediction and Entity Alignment. In the current experimental setting, multiple different scores are employed to assess different aspects of model performance. We analyze the informativeness of these evaluation measures and identify several shortcomings. In particular, we demonstrate that all existing scores can hardly be used to compare results across different datasets. Moreover, we demonstrate that varying size of the test size automatically has impact on the performance of the same model based on commonly used metrics for the Entity Alignment task. We show that this leads to various problems in the interpretation of results, which may support misleading conclusions. Therefore, we propose adjustments to the evaluation and demonstrate empirically how this supports a fair, comparable, and interpretable assessment of model performance.

inproceedings

DL4G @WWW 2020

5th International Workshop on Deep Learning for Graphs at the International World Wide Web Conference. Taipeh, Taiwan, Apr 21, 2020. Full paper at WI-AT 2020.