229 citations · 553 across the 32 of their papers we have counts for
3 papers · 1 filter
Improving Inductive Link Prediction Using Hyper-Relational Facts
Mehdi Ali, Max Berrendorf, Mikhail Galkin +4
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 i…
NodePiece: Compositional and Parameter-Efficient Representations of Large Knowledge Graphs
Mikhail Galkin, Etienne Denis, Jiapeng Wu +1
Conventional representation learning algorithms for knowledge graphs (KG) map each entity to a unique embedding vector. Such a shallow lookup results in a linear growth of memory c…
Query Embedding on Hyper-relational Knowledge Graphs
Dimitrios Alivanistos, Max Berrendorf, Michael Cochez +1
Multi-hop logical reasoning is an established problem in the field of representation learning on knowledge graphs (KGs). It subsumes both one-hop link prediction as well as other m…