Efficient Explainable Learning on Knowledge Graphs

Informazioni relative al progetto

ENEXA

ID dell’accordo di sovvenzione: 101070305

DOI 10.3030/101070305

Data della firma CE 13 Giugno 2022

Data di avvio 1 Ottobre 2022

Data di completamento 30 Settembre 2025

Finanziato da

• Digital, Industry and Space

Costo totale € 3 991 269,50

Contributo UE € 3 991 269,50

Coordinato da

UNIVERSITAET PADERBORN
Germany

Risultati finali

Other (3)

First version of KG representation approaches

This deliverable will describe the 1st version of the knowledge graph representation approaches developed in ENEXA. Implementation details and an evaluation of each approach against the existing state of the art will be presented.

First version of the explainable ML algorithms

This deliverable will describe the first version of the efficiency and explainability algorithms. Moreover, baseline implementations provided by ENEXA will be presented.

Preliminary version of the platform

Software release of the ENEXA platform after the first development phase including preliminary versions of the code, documentation and test scenarios.

Documents, reports (1)

Requirement specification

This deliverable will include the initial set of requirements identified from the users. This serves as a direct input for WP3 and WP4 in which the ENEXA approaches will be developed. It will also be used to evaluate the platform after the first development phase and plan development steps for the second development.

Pubblicazioni

Conference proceedings (12)

Learning Permutation-Invariant Embeddings for Description Logic Concepts

Autori: Caglar Demir, Axel-Cyrille Ngonga Ngomo
Pubblicato in: Advances in Intelligent Data Analysis XXI. Lecture Notes in Computer Science., Numero 13876, 2023
Editore: Springer, Cham
DOI: 10.1007/978-3-031-30047-9_9

Improving Graph-to-Text Generation Using Cycle Training

Autori: Fina Polat, Ilaria Tiddi, Paul Groth, Piek Vossen
Pubblicato in: Proceedings of the 4th Conference on Language, Data and Knowledge, 2023
Editore: NOVA CLUNL

Neural Class Expression Synthesis in ALCHIQ(D)

Autori: N'Dah Jean Kouagou, Stefan Heindorf, Caglar Demir, Axel-Cyrille Ngonga Ngomo
Pubblicato in: 2023
Editore: Springer

Clifford Embeddings – A Generalized Approach for Embedding in Normed Algebras

Autori: Caglar Demir, Axel-Cyrille Ngonga Ngomo
Pubblicato in: 2023
Editore: Springer

Explainable Integration of Knowledge Graphs using Large Language Models

Autori: Abdullah Fathi Ahmed, Asep Fajar Firmansyah, Mohamed Ahmed Sherif, Diego Moussallem, Axel-Cyrille Ngonga Ngomo
Pubblicato in: Natural Language Processing and Information Systems. Lecture Notes in Computer Science., Numero 13913, 2023
Editore: Springer, Cham
DOI: 10.1007/978-3-031-35320-8_9

TemporalFC: A Temporal Fact Checking approach over Knowledge Graphs

Autori: Umair Qudus, Michael Röder, Sabrina Kirrane, Axel-Cyrille Ngonga Ngomo
Pubblicato in: 2023
Editore: Springer

Do Instruction-tuned Large Language Models Help with Relation Extraction?

Autori: Xue Li, Fina Polat, Paul Groth
Pubblicato in: Joint proceedings of the KBC-LM workshop and the LM-KBC challenge at ISWC 2023, 2023, ISSN 1613-0073
Editore: CEUR Workshop Proceedings

Native Execution of GraphQL Queries over RDF Graphs Using Multi-way Joins

Autori: Nikolaos Karalis, Alexander Bigerl, Axel-Cyrille Ngonga Ngomo
Pubblicato in: 2023
Editore: IOS Press

Neuro-Symbolic Class Expression Learning

Autori: Caglar Demir, Axel-Cyrille Ngonga Ngomo
Pubblicato in: 2023
Editore: International Joint Conferences on Artificial Intelligence
DOI: 10.24963/ijcai.2023/403

Logics with probabilistic team semantics and the Boolean negation

Autori: Miika Hannula, Minna Hirvonen, Juha Kontinen, Yasir Mahmood, Arne Meier, Jonni Virtema
Pubblicato in: 2023
Editore: Springer

Neural Class Expression Synthesis

Autori: N’Dah Jean Kouagou, Stefan Heindorf, Caglar Demir, Axel-Cyrille Ngonga Ngomo
Pubblicato in: Proceedings of the 17th International Workshop on Neural-Symbolic Learning and Reasoning., Numero 3432, 2023, ISSN 1613-0073
Editore: CEUR Workshop Proceedings
DOI: 10.1007/978-3-031-33455-9_13

Parameterized Complexity of Propositional Inclusion and Independence Logic

Autori: Yasir Mahmood, Jonni Virtema
Pubblicato in: 2023
Editore: Springer

Peer reviewed articles (2)

Online event recognition over noisy data streams

Autori: Periklis Mantenoglou, Alexander Artikis, Georgios Paliouras
Pubblicato in: International Journal of Approximate Reasoning, Numero 161, 2023, ISSN 0888-613X
Editore: Elsevier BV
DOI: 10.1016/j.ijar.2023.108993

Semantic Web

Autori: Enrico
Pubblicato in: Semantic Web, 2023, ISSN 1570-0844
Editore: IOS Press
DOI: 10.3233/SW-233407