20 citations · 40 across the 26 of their papers we have counts for
8 papers · 1 filter
Neural Class Expression Synthesis
N'Dah Jean Kouagou, Stefan Heindorf, Caglar Demir +1
Many applications require explainable node classification in knowledge graphs. Towards this end, a popular ``white-box'' approach is class expression learning: Given sets of positi…
EvoLearner: Learning Description Logics with Evolutionary Algorithms
Stefan Heindorf, Lukas Blübaum, Nick Düsterhus +4
Classifying nodes in knowledge graphs is an important task, e.g., for predicting missing types of entities, predicting which molecules cause cancer, or predicting which drugs are p…
Learning Concept Lengths Accelerates Concept Learning in ALC
N'Dah Jean Kouagou, Stefan Heindorf, Caglar Demir +1
Concept learning approaches based on refinement operators explore partially ordered solution spaces to compute concepts, which are used as binary classification models for individu…
DRILL-- Deep Reinforcement Learning for Refinement Operators in
Caglar Demir, Axel-Cyrille Ngonga Ngomo
Approaches based on refinement operators have been successfully applied to class expression learning on RDF knowledge graphs. These approaches often need to explore a large number…
Convolutional Hypercomplex Embeddings for Link Prediction
Caglar Demir, Diego Moussallem, Stefan Heindorf +1
Knowledge graph embedding research has mainly focused on the two smallest normed division algebras, and . Recent results suggest that trilinear products of…
Out-of-Vocabulary Entities in Link Prediction
Caglar Demir, Axel-Cyrille Ngonga Ngomo
Knowledge graph embedding techniques are key to making knowledge graphs amenable to the plethora of machine learning approaches based on vector representations. Link prediction is…
MLCheck- Property-Driven Testing of Machine Learning Models
Arnab Sharma, Caglar Demir, Axel-Cyrille Ngonga Ngomo +1
In recent years, we observe an increasing amount of software with machine learning components being deployed. This poses the question of quality assurance for such components: how…
A shallow neural model for relation prediction
Caglar Demir, Diego Moussallem, Axel-Cyrille Ngonga Ngomo
Knowledge graph completion refers to predicting missing triples. Most approaches achieve this goal by predicting entities, given an entity and a relation. We predict missing triple…