no code implementations • 6 Feb 2024 • Louis Mozart Kamdem, Caglar Demir, Axel-Cyrille Ngonga
We propose to consider nilpotent base vectors with a nilpotency index of two.
1 code implementation • 23 Oct 2023 • N'Dah Jean Kouagou, Caglar Demir, Hamada M. Zahera, Adrian Wilke, Stefan Heindorf, Jiayi Li, Axel-Cyrille Ngonga Ngomo
Most of them obtain embeddings by learning the structure of the knowledge graph within a link prediction setting.
1 code implementation • 28 Apr 2023 • Caglar Demir, Michel Wiebesiek, Renzhong Lu, Axel-Cyrille Ngonga Ngomo, Stefan Heindorf
We evaluate LitCQD on query types with and without literal values.
1 code implementation • 3 Mar 2023 • Caglar Demir, Axel-Cyrille Ngonga Ngomo
We reformulate the learning problem as a multi-label classification problem and propose a neural embedding model (NERO) that learns permutation-invariant embeddings for sets of examples tailored towards predicting $F_1$ scores of pre-selected description logic concepts.
1 code implementation • 18 Jul 2022 • Caglar Demir, Axel-Cyrille Ngonga Ngomo
Knowledge graph embedding research has mainly focused on learning continuous representations of knowledge graphs towards the link prediction problem.
1 code implementation • 30 May 2022 • Julian Lienen, Caglar Demir, Eyke Hüllermeier
One such method, so-called credal self-supervised learning, maintains pseudo-supervision in the form of sets of (instead of single) probability distributions over labels, thereby allowing for a flexible yet uncertainty-aware labeling.
1 code implementation • 13 May 2022 • Caglar Demir, Julian Lienen, Axel-Cyrille Ngonga Ngomo
Our experiments suggest that applying Kronecker decomposition on embedding matrices leads to an improved parameter efficiency on all benchmark datasets.
no code implementations • 16 Nov 2021 • N'Dah Jean Kouagou, Stefan Heindorf, Caglar Demir, Axel-Cyrille Ngonga Ngomo
Our main intuition is that class expression learning can be regarded as a translation problem.
1 code implementation • 8 Nov 2021 • Stefan Heindorf, Lukas Blübaum, Nick Düsterhus, Till Werner, Varun Nandkumar Golani, Caglar Demir, Axel-Cyrille Ngonga Ngomo
We contribute a novel initialization method for the initial population: starting from positive examples, we perform biased random walks and translate them to description logic concepts.
1 code implementation • 10 Jul 2021 • N'Dah Jean Kouagou, Stefan Heindorf, Caglar Demir, Axel-Cyrille Ngonga Ngomo
We then extend the CELOE algorithm, which learns ALC concepts, with our concept length predictor.
1 code implementation • 29 Jun 2021 • Caglar Demir, Diego Moussallem, Stefan Heindorf, Axel-Cyrille Ngonga Ngomo
We propose the four approaches QMult, OMult, ConvQ and ConvO to tackle the link prediction problem.
1 code implementation • 29 Jun 2021 • Caglar Demir, Axel-Cyrille Ngonga Ngomo
In this work, we leverage deep reinforcement learning to accelerate the learning of concepts in $\mathcal{ALC}$ by proposing DRILL -- a novel class expression learning approach that uses a convolutional deep Q-learning model to steer its search.
1 code implementation • 26 May 2021 • Caglar Demir, Axel-Cyrille Ngonga Ngomo
As benchmarks are crucial for the fair comparison of algorithms, ensuring their quality is tantamount to providing a solid ground for developing better solutions to link prediction and ipso facto embedding knowledge graphs.
1 code implementation • 22 Jan 2021 • Caglar Demir, Diego Moussallem, Axel-Cyrille Ngonga Ngomo
We predict missing triples via the relation prediction.
1 code implementation • 7 Aug 2020 • Caglar Demir, Axel-Cyrille Ngonga Ngomo
In this paper, we study the problem of learning continuous vector representations of knowledge graphs for predicting missing links.
1 code implementation • 21 Jan 2020 • Caglar Demir, Axel-Cyrille Ngonga Ngomo
We present a novel and scalable paradigm for the computation of knowledge graph embeddings, which we dub PYKE .