Inductive Link Prediction Using Hyper-Relational Facts



  • Veronika Thost
  • Mehdi Ali
  • Mikhail Galkin
  • Tengfei Ma
  • Max Berrendorf
  • Volker Tresp
  • Jens Lehmann

Published on


For many years, link prediction on knowledge. graphs 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.

Please cite our work using the BibTeX below.

  title     = {Improving Inductive Link Prediction Using Hyper-Relational Facts (Extended Abstract)},
  author    = {Ali, Mehdi and Berrendorf, Max and Galkin, Mikhail and Thost, Veronika and Ma, Tengfei and Tresp, Volker and Lehmann, Jens},
  booktitle = {Proceedings of the Thirty-First International Joint Conference on
               Artificial Intelligence, {IJCAI-22}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Lud De Raedt},
  pages     = {5259--5263},
  year      = {2022},
  month     = {7},
  note      = {Sister Conferences Best Papers},
  doi       = {10.24963/ijcai.2022/731},
  url       = {},
Close Modal