Interpreting Link Prediction on Knowledge Graphs

Link Prediction (LP) on Knowledge Graphs (KGs) has re-cently become a sparkling research topic, benefiting from the explosion of machine learning techniques. Several relation-learning models are pub-lished every year, mostly relying on KG embeddings. So far, however, not much has been done to interpret the features they learn and predict, and the circumstances that allow them to achieve satisfactory performances. Our research aims at opening the black box of LP models, trying to explain their behaviors. In this work we first discuss the current lim-itations of LP benchmarks, showing how the use of global metrics on largely skewed datasets hinders our understanding of these models; we then report the main takeaways from our recent comparative analysis of state-of-the-art LP models [3], identifying the most inuential structural features of the graph for predictive effectiveness.