08.11.2021

Max Berrendorf and Volker Tresp Receive Best Paper Award at ISWC 2021

Honored for Improving Inductive Link Prediction Using Hyper-Relational Facts

Congrats to our Junior Member Max Berrendorf and our PI Volker Tresp for receiving the Best Paper Award in the Research Track at the International Semantic Web Conference (ISWC 2021) for their work "Improving Inductive Link Prediction Using Hyper-Relational Facts".

M. Ali, M. Berrendorf, M. Galkin, V. Thost, T. Ma, V. Tresp and J. Lehmann.
Improving Inductive Link Prediction Using Hyper-Relational Facts.
ISWC 2021 - 20th International Semantic Web Conference. Virtual, Oct 24-28, 2021. Best Paper. DOI GitHub

Abstract

For many years, link prediction on knowledge graphs (KGs) has been a purely transductive task, not allowing for reasoning on unseen entities. Recently, increasing efforts are put into exploring semi- and fully inductive scenarios, enabling inference over unseen and emerging entities. Still, all these approaches only consider triple-based KGs, whereas their richer counterparts, hyper-relational KGs (e.g., Wikidata), have not yet been properly studied. In this work, we classify different inductive settings and study the benefits of employing hyper-relational KGs on a wide range of semi- and fully inductive link prediction tasks powered by recent advancements in graph neural networks. Our experiments on a novel set of benchmarks show that qualifiers over typed edges can lead to performance improvements of 6% of absolute gains (for the Hits@10 metric) compared to triple-only baselines.

MCML Authors