DeepAI AI Chat
Log In Sign Up

Improving Inductive Link Prediction Using Hyper-Relational Facts

by   Mehdi Ali, et al.

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 kg, 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 (for the Hits@10 metric) compared to triple-only baselines. Our code is available at <>.


page 1

page 2

page 3

page 4


Inductive Logical Query Answering in Knowledge Graphs

Formulating and answering logical queries is a standard communication in...

Disconnected Emerging Knowledge Graph Oriented Inductive Link Prediction

Inductive link prediction (ILP) is to predict links for unseen entities ...

DHGE: Dual-view Hyper-Relational Knowledge Graph Embedding for Link Prediction and Entity Typing

In the field of representation learning on knowledge graphs (KGs), a hyp...

HYPER^2: Hyperbolic Poincare Embedding for Hyper-Relational Link Prediction

Link Prediction, addressing the issue of completing KGs with missing fac...

Inductive Relation Prediction from Relational Paths and Context with Hierarchical Transformers

Relation prediction on knowledge graphs (KGs) is a key research topic. D...

Message Passing for Hyper-Relational Knowledge Graphs

Hyper-relational knowledge graphs (KGs) (e.g., Wikidata) enable associat...

Evaluating Graph Neural Networks for Link Prediction: Current Pitfalls and New Benchmarking

Link prediction attempts to predict whether an unseen edge exists based ...