EL Embeddings: Geometric construction of models for the Description Logic EL ++

Kulmanov, Maxat; Liu-Wei, Wang; Hoehndorf, Robert

doi:10.48550/arxiv.1902.10499

Cited by 7 publications

(9 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An n-ball usually refers to a ball in an ndimensional Euclidean space. The EL embeddings study [14] attempts to encode logical axioms by positioning n-balls. We explain how it works for encoding subsumption and disjointness as they are the most relevant to our work.…”

Section: N-balls and El Embeddingsmentioning

confidence: 99%

“…We build upon the EL embedding technique [14] to learn a set of n-balls for all concepts O in the ontology O, which is referred to as a concept embedding. We extract subsumption and disjointness axioms to define the class hierarchy of the ontology O.…”

Section: Concept N-ball Embeddingsmentioning

confidence: 99%

“…Overall, we extend [14] to capture knowledge from an ontology in the form of n-ball embeddings and show that they are favourable for the downstream vision task of few-shot image classification. This is also coupled with a technique to measure the quality of the learnt embeddings with respect to the knowledge entailed by the ontology.…”

Section: Introductionmentioning

confidence: 98%

“…This embedding can represent specialisations (e.g., Dog SubclassOf Animal) using the property of one n-ball enclosing another and partonomies (e.g., Dog has-Part Tail) using translations of n-ball positions. In this study, we directly utilise two loss design components of [14] to capture subsumption and disjointness axioms, while extending their approach with more regularisation components in order to embed large hierarchies in a favourable manner for a downstream vision task. Additionally, we propose the use of the inferred class hierarchy of the input ontology and introduce a technique to evaluate the quality of the learnt embeddings during the embedding learning process.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Ontology-based n-ball Concept Embeddings Informing Few-shot Image Classification

Jayathilaka,

Mu,

Sattler

2021

Preprint

View full text Add to dashboard Cite

We propose a novel framework named ViOCE that integrates ontology-based background knowledge in the form of n-ball concept embeddings into a neural network based vision architecture. The approach consists of two components -converting symbolic knowledge of an ontology into continuous space by learning n-ball embeddings that capture properties of subsumption and disjointness, and guiding the training and inference of a vision model using the learnt embeddings. We evaluate ViOCE using the task of few-shot image classification, where it demonstrates superior performance on two standard benchmarks.

show abstract

Section: N-balls and El Embeddingsmentioning

confidence: 99%

Section: Concept N-ball Embeddingsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 98%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Ontology-based n-ball Concept Embeddings Informing Few-shot Image Classification

Jayathilaka,

Mu,

Sattler

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Considering that KGs are often incomplete and noisy, the KEEN Universe can be applied in numerous applications to derive new facts. For instance, the KEEN Universe has been used on scholarly KGs to provide research recommendations [14] and on biomedical KGs to predict associations between biomedical entities [3,17]. Moreover, it can be used in downstream tasks like QA and dialogue generation [6,19].…”

Section: Impactmentioning

confidence: 99%

The KEEN Universe

Ali

Jabeen

Hoyt

et al. 2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

There is an emerging trend of embedding knowledge graphs (KGs) in continuous vector spaces in order to use those for machine learning tasks. Recently, many knowledge graph embedding (KGE) models have been proposed that learn low dimensional representations while trying to maintain the structural properties of the KGs such as the similarity of nodes depending on their edges to other nodes. KGEs can be used to address tasks within KGs such as the prediction of novel links and the disambiguation of entities. They can also be used for downstream tasks like question answering and fact-checking. Overall, these tasks are relevant for the semantic web community. Despite their popularity, the reproducibility of KGE experiments and the transferability of proposed KGE models to research fields outside the machine learning community can be a major challenge. Therefore, we present the KEEN Universe, an ecosystem for knowledge graph embeddings that we have developed with a strong focus on reproducibility and transferability. The KEEN Universe currently consists of the Python packages PyKEEN (Python KnowlEdge EmbeddiNgs), BioKEEN (Biological KnowlEdge EmbeddiNgs), and the KEEN Model Zoo for sharing trained KGE models with the community.

show abstract