Improving Knowledge Graph Embeddings with Ontological Reasoning

Jain, N. K.; Tran, Trung-Kien; Gad-Elrab, Mohamed H.; Stepanova, Daria

doi:10.1007/978-3-030-88361-4_24

Cited by 20 publications

(27 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The possibility of using additional semantic information has been extensively studied in recent works [ Jain et al , 2021a, Krompaß et al , 2015, Niu et al , 2020, Cui et al , 2021, Xie et al , 2016, Lv et al , 2018, Wang et al , 2021b. In general, the semantic information stems directly from an ontology, originally defined by Gruber as an "explicit specification of a conceptualization" [ Gruber , 1993 ].…”

Section: Combining Embeddings and Semanticsmentioning

confidence: 99%

“…Training a Knowledge Graph Embedding Model (KGEM) firstly requires corrupting existing triples by replacing either their head h or their tail t with another entity to generate negative counterparts. This procedure is called negative sampling [ Bordes et al , 2013, Krompaß et al , 2015, Jain et al , 2021a.…”

Section: Introductionmentioning

confidence: 99%

“…More importantly, they only provide a partial picture of KGEM performance [ Berrendorf et al , 2020 ]. Indeed, LP can lead to nonsensical triples, such as (BarackObama,isFatherOf,USA), being predicted as highly plausible facts, although they violate constraints on the domain and range of relations [ Jain et al , 2021a. KGEMs with such issues may nevertheless reach a satisfying performance in terms of rank-based metrics.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Sem@$K$: Is my knowledge graph embedding model semantic-aware?

Hubert¹,

Monnin²,

Brun³

et al. 2023

Preprint

View full text Add to dashboard Cite

Using knowledge graph embedding models (KGEMs) is a popular approach for predicting links in knowledge graphs (KGs). Traditionally, the performance of KGEMs for link prediction is assessed using rank-based metrics, which evaluate their ability to give high scores to ground-truth entities. However, the literature claims that the KGEM evaluation procedure would benefit from adding supplementary dimensions to assess. That is why, in this paper, we extend our previously introduced metric Sem@K that measures the capability of models to predict valid entities w.r.t. domain and range constrains. In particular, we consider a broad range of KGs and take their respective characteristics into account to propose different versions of Sem@K. We also perform an extensive study of KGEM semantic awareness. Our experiments show that Sem@K provides a new perspective on KGEM quality. Its joint analysis with rank-based metrics offer different conclusions on the predictive power of models. Regarding Sem@K, some KGEMs are inherently better than others, but this semantic superiority is not indicative of their performance w.r.t. rank-based metrics. In this work, we generalize conclusions about the relative performance of KGEMs w.r.t. rank-based and semantic-oriented metrics at the level of families of models. The joint analysis of the aforementioned metrics gives more insight into the peculiarities of each model. This work paves the way for a more comprehensive evaluation of KGEM adequacy for specific downstream tasks.

show abstract

Section: Combining Embeddings and Semanticsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Sem@$K$: Is my knowledge graph embedding model semantic-aware?

Hubert¹,

Monnin²,

Brun³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Therefore, more sophisticated methods have been proposed to generate high-quality negative samples and consequently give more hints to the model training [30]. In particular, ontological constraints and domain knowledge can be leveraged to create meaningful negative samples [10,13,26]. Intuitively, generating more realistic and robust negative samples helps the embedding model learn a better vector representation of the graph components.…”

Section: Negative Sampling For Link Prediction In Knowledge Graphsmentioning

confidence: 99%

New Strategies for Learning Knowledge Graph Embeddings: The Recommendation Case

Hubert

Monnin

Brun

et al. 2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Knowledge graph embedding models encode elements of a graph into a low-dimensional space that supports several downstream tasks. This work is concerned with the recommendation task, which we approach as a link prediction task on a single target relation performed in the embedding space. Training an embedding model requires negative sampling, which consists in corrupting the head or the tail of positive triples to generate negative ones. Although knowledge graph embedding models and negative sampling have extensively been investigated for link prediction, their combined use for performing recommendations over knowledge graphs remains largely unexplored in the literature. In this work, we propose two specialization strategies for training embedding models and performing knowledge graph-based recommendations. Both strategies first train an embedding model on the whole knowledge graph. Then, during a specialization phase, a dedicated negative sampling scheme is applied to refine the pre-trained model. Experimental results on two public datasets demonstrate that a simple strategy which refines a pre-trained model by sampling random negative tails for the target relation proves to be very effective. This strategy significantly improves performance with respect to traditional rank-based evaluation metrics as well as a newly introduced metric that reflects the semantic validity of the top-ranked candidate entities.

show abstract

“…In fact, [4] states that most existing KGEs are not capable of encoding ontological information. [5] use ontological information but only for improving the negative samples that KGEs require.…”

Section: Introductionmentioning

confidence: 99%

Towards Loosely-Coupling Knowledge Graph Embeddings and Ontology-based Reasoning

Kaoudi¹,

Lorenzo²,

Markl³

2022

Preprint

View full text Add to dashboard Cite

Knowledge graph completion (a.k.a. link prediction), i.e., the task of inferring missing information from knowledge graphs, is a widely used task in many applications, such as product recommendation and question answering. The state-of-the-art approaches of knowledge graph embeddings and/or rule mining and reasoning are datadriven and, thus, solely based on the information the input knowledge graph contains. This leads to unsatisfactory prediction results which make such solutions inapplicable to crucial domains such as healthcare. To further enhance the accuracy of knowledge graph completion we propose to loosely-couple the data-driven power of knowledge graph embeddings with domain-specific reasoning stemming from experts or entailment regimes (e.g., OWL2). In this way, we not only enhance the prediction accuracy with domain knowledge that may not be included in the input knowledge graph but also allow users to plugin their own knowledge graph embedding and reasoning method. Our initial results show that we enhance the MRR accuracy of vanilla knowledge graph embeddings by up to 3x and outperform hybrid solutions that combine knowledge graph embeddings with rule mining and reasoning up to 3.5x MRR.

show abstract

Improving Knowledge Graph Embeddings with Ontological Reasoning

Cited by 20 publications

References 26 publications

Sem@$K$: Is my knowledge graph embedding model semantic-aware?

Sem@$K$: Is my knowledge graph embedding model semantic-aware?

New Strategies for Learning Knowledge Graph Embeddings: The Recommendation Case

Towards Loosely-Coupling Knowledge Graph Embeddings and Ontology-based Reasoning

Contact Info

Product

Resources

About