---
_id: '61041'
abstract:
- lang: eng
text: Large Language Models (LLMs) are increasingly deployed in real-world applications
that require access to up-to-date knowledge. However, retraining LLMs is computationally
expensive. Therefore, knowledge editing techniques are crucial for maintaining
current information and correcting erroneous assertions within pre-trained models.
Current benchmarks for knowledge editing primarily focus on recalling edited facts,
often neglecting their logical consequences. To address this limitation, we introduce
a new benchmark designed to evaluate how knowledge editing methods handle the
logical consequences of a single fact edit. Our benchmark extracts relevant logical
rules from a knowledge graph for a given edit. Then, it generates multi-hop questions
based on these rules to assess the impact on logical consequences. Our findings
indicate that while existing knowledge editing approaches can accurately insert
direct assertions into LLMs, they frequently fail to inject entailed knowledge.
Specifically, experiments with popular methods like ROME and FT reveal a substantial
performance gap, up to 24%, between evaluations on directly edited knowledge and
on entailed knowledge. This highlights the critical need for semantics-aware evaluation
frameworks in knowledge editing.
author:
- first_name: Tatiana
full_name: Moteu Ngoli, Tatiana
id: '99174'
last_name: Moteu Ngoli
- first_name: N'Dah Jean
full_name: Kouagou, N'Dah Jean
id: '87189'
last_name: Kouagou
- first_name: Hamada Mohamed Abdelsamee
full_name: Zahera, Hamada Mohamed Abdelsamee
id: '72768'
last_name: Zahera
orcid: 0000-0003-0215-1278
- first_name: Axel-Cyrille
full_name: Ngonga Ngomo, Axel-Cyrille
id: '65716'
last_name: Ngonga Ngomo
citation:
ama: 'Moteu Ngoli T, Kouagou NJ, Zahera HMA, Ngonga Ngomo A-C. Benchmarking Knowledge
Editing using Logical Rules. In: Proceedings of the 24th International Semantic
Web Conference (ISWC 2025). Springer, Cham; 2025:pp 41-56. doi:https://doi.org/10.1007/978-3-032-09530-5_3'
apa: Moteu Ngoli, T., Kouagou, N. J., Zahera, H. M. A., & Ngonga Ngomo, A.-C.
(2025). Benchmarking Knowledge Editing using Logical Rules. Proceedings of
the 24th International Semantic Web Conference (ISWC 2025), pp 41-56. https://doi.org/10.1007/978-3-032-09530-5_3
bibtex: '@inproceedings{Moteu Ngoli_Kouagou_Zahera_Ngonga Ngomo_2025, title={Benchmarking
Knowledge Editing using Logical Rules}, DOI={https://doi.org/10.1007/978-3-032-09530-5_3},
booktitle={Proceedings of the 24th International Semantic Web Conference (ISWC
2025)}, publisher={Springer, Cham}, author={Moteu Ngoli, Tatiana and Kouagou,
N’Dah Jean and Zahera, Hamada Mohamed Abdelsamee and Ngonga Ngomo, Axel-Cyrille},
year={2025}, pages={pp 41-56} }'
chicago: Moteu Ngoli, Tatiana, N’Dah Jean Kouagou, Hamada Mohamed Abdelsamee Zahera,
and Axel-Cyrille Ngonga Ngomo. “Benchmarking Knowledge Editing Using Logical Rules.”
In Proceedings of the 24th International Semantic Web Conference (ISWC 2025),
pp 41-56. Springer, Cham, 2025. https://doi.org/10.1007/978-3-032-09530-5_3.
ieee: 'T. Moteu Ngoli, N. J. Kouagou, H. M. A. Zahera, and A.-C. Ngonga Ngomo, “Benchmarking
Knowledge Editing using Logical Rules,” in Proceedings of the 24th International
Semantic Web Conference (ISWC 2025), Nara, Japan, 2025, p. pp 41-56, doi:
https://doi.org/10.1007/978-3-032-09530-5_3.'
mla: Moteu Ngoli, Tatiana, et al. “Benchmarking Knowledge Editing Using Logical
Rules.” Proceedings of the 24th International Semantic Web Conference (ISWC
2025), Springer, Cham, 2025, p. pp 41-56, doi:https://doi.org/10.1007/978-3-032-09530-5_3.
short: 'T. Moteu Ngoli, N.J. Kouagou, H.M.A. Zahera, A.-C. Ngonga Ngomo, in: Proceedings
of the 24th International Semantic Web Conference (ISWC 2025), Springer, Cham,
2025, p. pp 41-56.'
conference:
end_date: 2025.11.6
location: Nara, Japan
name: The 24th International Semantic Web Conference (ISWC 2025)
start_date: 2025.11.2
date_created: 2025-08-27T13:17:55Z
date_updated: 2025-12-01T10:04:25Z
department:
- _id: '574'
doi: https://doi.org/10.1007/978-3-032-09530-5_3
keyword:
- dice sailproject moteu kouagou zahera ngonga
language:
- iso: eng
page: pp 41-56
project:
- _id: '285'
name: SAIL - Nachhaltiger Lebenszyklus von intelligenten soziotechnischen Systemen
publication: Proceedings of the 24th International Semantic Web Conference (ISWC 2025)
publication_identifier:
isbn:
- 978-3-032-09530-5
publication_status: published
publisher: Springer, Cham
status: public
title: Benchmarking Knowledge Editing using Logical Rules
type: conference
user_id: '99174'
year: '2025'
...
---
_id: '63574'
author:
- first_name: Quannian
full_name: Zhang, Quannian
id: '104099'
last_name: Zhang
orcid: 0009-0008-9497-3204
- first_name: Michael
full_name: Röder, Michael
id: '67199'
last_name: Röder
orcid: https://orcid.org/0000-0002-8609-8277
- first_name: Nikit
full_name: Srivastava, Nikit
id: '70066'
last_name: Srivastava
orcid: 0009-0004-5164-4911
- first_name: N'Dah Jean
full_name: KOUAGOU, N'Dah Jean
id: '87189'
last_name: KOUAGOU
- first_name: Axel-Cyrille
full_name: Ngonga Ngomo, Axel-Cyrille
id: '65716'
last_name: Ngonga Ngomo
citation:
ama: 'Zhang Q, Röder M, Srivastava N, KOUAGOU NJ, Ngonga Ngomo A-C. Explainable
Benchmarking through the Lense of Concept Learning. In: Proceedings of the
Knowledge Capture Conference 2025. ACM; 2025. doi:10.1145/3731443.3771359'
apa: Zhang, Q., Röder, M., Srivastava, N., KOUAGOU, N. J., & Ngonga Ngomo, A.-C.
(2025). Explainable Benchmarking through the Lense of Concept Learning. Proceedings
of the Knowledge Capture Conference 2025. https://doi.org/10.1145/3731443.3771359
bibtex: '@inproceedings{Zhang_Röder_Srivastava_KOUAGOU_Ngonga Ngomo_2025, title={Explainable
Benchmarking through the Lense of Concept Learning}, DOI={10.1145/3731443.3771359},
booktitle={Proceedings of the Knowledge Capture Conference 2025}, publisher={ACM},
author={Zhang, Quannian and Röder, Michael and Srivastava, Nikit and KOUAGOU,
N’Dah Jean and Ngonga Ngomo, Axel-Cyrille}, year={2025} }'
chicago: Zhang, Quannian, Michael Röder, Nikit Srivastava, N’Dah Jean KOUAGOU, and
Axel-Cyrille Ngonga Ngomo. “Explainable Benchmarking through the Lense of Concept
Learning.” In Proceedings of the Knowledge Capture Conference 2025. ACM,
2025. https://doi.org/10.1145/3731443.3771359.
ieee: 'Q. Zhang, M. Röder, N. Srivastava, N. J. KOUAGOU, and A.-C. Ngonga Ngomo,
“Explainable Benchmarking through the Lense of Concept Learning,” 2025, doi: 10.1145/3731443.3771359.'
mla: Zhang, Quannian, et al. “Explainable Benchmarking through the Lense of Concept
Learning.” Proceedings of the Knowledge Capture Conference 2025, ACM, 2025,
doi:10.1145/3731443.3771359.
short: 'Q. Zhang, M. Röder, N. Srivastava, N.J. KOUAGOU, A.-C. Ngonga Ngomo, in:
Proceedings of the Knowledge Capture Conference 2025, ACM, 2025.'
date_created: 2026-01-12T17:21:05Z
date_updated: 2026-01-12T17:25:00Z
department:
- _id: '574'
- _id: '923'
doi: 10.1145/3731443.3771359
language:
- iso: eng
publication: Proceedings of the Knowledge Capture Conference 2025
publication_status: published
publisher: ACM
status: public
title: Explainable Benchmarking through the Lense of Concept Learning
type: conference
user_id: '67199'
year: '2025'
...
---
_id: '54449'
author:
- first_name: N'Dah Jean
full_name: KOUAGOU, N'Dah Jean
id: '87189'
last_name: KOUAGOU
- first_name: Caglar
full_name: Demir, Caglar
id: '43817'
last_name: Demir
- first_name: Hamada Mohamed Abdelsamee
full_name: Zahera, Hamada Mohamed Abdelsamee
id: '72768'
last_name: Zahera
orcid: 0000-0003-0215-1278
- first_name: Adrian
full_name: Wilke, Adrian
id: '9101'
last_name: Wilke
orcid: 0000-0002-6575-807X
- first_name: Stefan
full_name: Heindorf, Stefan
id: '11871'
last_name: Heindorf
orcid: 0000-0002-4525-6865
- first_name: Jiayi
full_name: Li, Jiayi
last_name: Li
- first_name: Axel-Cyrille
full_name: Ngonga Ngomo, Axel-Cyrille
id: '65716'
last_name: Ngonga Ngomo
citation:
ama: 'KOUAGOU NJ, Demir C, Zahera HMA, et al. Universal Knowledge Graph Embeddings.
In: Companion Proceedings of the ACM on Web Conference 2024. ACM; 2024.
doi:10.1145/3589335.3651978'
apa: KOUAGOU, N. J., Demir, C., Zahera, H. M. A., Wilke, A., Heindorf, S., Li, J.,
& Ngonga Ngomo, A.-C. (2024). Universal Knowledge Graph Embeddings. Companion
Proceedings of the ACM on Web Conference 2024. Companion Proceedings of the
ACM on Web Conference 2024, Singapore. https://doi.org/10.1145/3589335.3651978
bibtex: '@inproceedings{KOUAGOU_Demir_Zahera_Wilke_Heindorf_Li_Ngonga Ngomo_2024,
title={Universal Knowledge Graph Embeddings}, DOI={10.1145/3589335.3651978},
booktitle={Companion Proceedings of the ACM on Web Conference 2024}, publisher={ACM},
author={KOUAGOU, N’Dah Jean and Demir, Caglar and Zahera, Hamada Mohamed Abdelsamee
and Wilke, Adrian and Heindorf, Stefan and Li, Jiayi and Ngonga Ngomo, Axel-Cyrille},
year={2024} }'
chicago: KOUAGOU, N’Dah Jean, Caglar Demir, Hamada Mohamed Abdelsamee Zahera, Adrian
Wilke, Stefan Heindorf, Jiayi Li, and Axel-Cyrille Ngonga Ngomo. “Universal Knowledge
Graph Embeddings.” In Companion Proceedings of the ACM on Web Conference 2024.
ACM, 2024. https://doi.org/10.1145/3589335.3651978.
ieee: 'N. J. KOUAGOU et al., “Universal Knowledge Graph Embeddings,” presented
at the Companion Proceedings of the ACM on Web Conference 2024, Singapore, 2024,
doi: 10.1145/3589335.3651978.'
mla: KOUAGOU, N’Dah Jean, et al. “Universal Knowledge Graph Embeddings.” Companion
Proceedings of the ACM on Web Conference 2024, ACM, 2024, doi:10.1145/3589335.3651978.
short: 'N.J. KOUAGOU, C. Demir, H.M.A. Zahera, A. Wilke, S. Heindorf, J. Li, A.-C.
Ngonga Ngomo, in: Companion Proceedings of the ACM on Web Conference 2024, ACM,
2024.'
conference:
end_date: 2024-05-17
location: Singapore
name: Companion Proceedings of the ACM on Web Conference 2024
start_date: 2024-05-13
date_created: 2024-05-26T18:52:47Z
date_updated: 2024-05-26T19:06:10Z
department:
- _id: '760'
- _id: '574'
doi: 10.1145/3589335.3651978
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://dl.acm.org/doi/abs/10.1145/3589335.3651978
oa: '1'
publication: Companion Proceedings of the ACM on Web Conference 2024
publication_status: published
publisher: ACM
status: public
title: Universal Knowledge Graph Embeddings
type: conference
user_id: '11871'
year: '2024'
...
---
_id: '58049'
abstract:
- lang: eng
text: In recent years, knowledge graph embedding models have been successfully applied
in the transductive setting to tackle various challenging tasks including link
prediction, and query answering. Yet, the transductive setting does not allow
for reasoning over unseen entities, relations, let alone numerical or non-numerical
literals. Although increasing efforts are put into exploring inductive scenarios,
inference over unseen entities, relations, and literals has yet to come. This
limitation prohibits the existing methods from handling real-world dynamic knowledge
graphs involving heterogeneous information about the world. Here, we propose a
remedy to this limitation. We propose the attentive byte-pair encoding layer (BytE)
to construct a triple embedding from a sequence of byte-pair encoded subword units
of entities and relations. Compared to the conventional setting, BytE leads to
massive feature reuse via weight tying, since it forces a knowledge graph embedding
model to learn embeddings for subword units instead of entities and relations
directly. Consequently, the size of the embedding matrices are not anymore bound
to the unique number of entities and relations of a knowledge graph. Experimental
results show that BytE improves the link prediction performance of 4 knowledge
graph embedding models on datasets where the syntactic representations of triples
are semantically meaningful. However, benefits of training a knowledge graph embedding
model with BytE dissipate on knowledge graphs where entities and relations are
represented with plain numbers or URIs. We provide an open source implementation
of BytE to foster reproducible research.
author:
- first_name: Caglar
full_name: Demir, Caglar
id: '43817'
last_name: Demir
- first_name: N'Dah Jean
full_name: KOUAGOU, N'Dah Jean
id: '87189'
last_name: KOUAGOU
- first_name: Arnab
full_name: Sharma, Arnab
id: '67200'
last_name: Sharma
- first_name: Axel-Cyrille
full_name: Ngonga Ngomo, Axel-Cyrille
id: '65716'
last_name: Ngonga Ngomo
citation:
ama: Demir C, KOUAGOU NJ, Sharma A, Ngonga Ngomo A-C. Inference over Unseen Entities,
Relations and Literals on Knowledge Graphs. Arxiv. Published online 2024.
doi:10.48550/ARXIV.2410.06742
apa: Demir, C., KOUAGOU, N. J., Sharma, A., & Ngonga Ngomo, A.-C. (2024). Inference
over Unseen Entities, Relations and Literals on Knowledge Graphs. Arxiv.
https://doi.org/10.48550/ARXIV.2410.06742
bibtex: '@article{Demir_KOUAGOU_Sharma_Ngonga Ngomo_2024, title={Inference over
Unseen Entities, Relations and Literals on Knowledge Graphs}, DOI={10.48550/ARXIV.2410.06742},
journal={Arxiv}, author={Demir, Caglar and KOUAGOU, N’Dah Jean and Sharma, Arnab
and Ngonga Ngomo, Axel-Cyrille}, year={2024} }'
chicago: Demir, Caglar, N’Dah Jean KOUAGOU, Arnab Sharma, and Axel-Cyrille Ngonga
Ngomo. “Inference over Unseen Entities, Relations and Literals on Knowledge Graphs.”
Arxiv, 2024. https://doi.org/10.48550/ARXIV.2410.06742.
ieee: 'C. Demir, N. J. KOUAGOU, A. Sharma, and A.-C. Ngonga Ngomo, “Inference over
Unseen Entities, Relations and Literals on Knowledge Graphs,” Arxiv, 2024,
doi: 10.48550/ARXIV.2410.06742.'
mla: Demir, Caglar, et al. “Inference over Unseen Entities, Relations and Literals
on Knowledge Graphs.” Arxiv, 2024, doi:10.48550/ARXIV.2410.06742.
short: C. Demir, N.J. KOUAGOU, A. Sharma, A.-C. Ngonga Ngomo, Arxiv (2024).
date_created: 2025-01-06T12:19:39Z
date_updated: 2025-01-07T20:01:36Z
doi: 10.48550/ARXIV.2410.06742
language:
- iso: eng
publication: Arxiv
status: public
title: Inference over Unseen Entities, Relations and Literals on Knowledge Graphs
type: journal_article
user_id: '67200'
year: '2024'
...
---
_id: '58048'
author:
- first_name: Arnab
full_name: Sharma, Arnab
id: '67200'
last_name: Sharma
- first_name: N'Dah Jean
full_name: KOUAGOU, N'Dah Jean
id: '87189'
last_name: KOUAGOU
- first_name: Axel-Cyrille
full_name: Ngonga Ngomo, Axel-Cyrille
id: '65716'
last_name: Ngonga Ngomo
citation:
ama: Sharma A, KOUAGOU NJ, Ngonga Ngomo A-C. Resilience in Knowledge Graph Embeddings.
Arxiv. Published online 2024. doi:10.48550/ARXIV.2410.21163
apa: Sharma, A., KOUAGOU, N. J., & Ngonga Ngomo, A.-C. (2024). Resilience in
Knowledge Graph Embeddings. Arxiv. https://doi.org/10.48550/ARXIV.2410.21163
bibtex: '@article{Sharma_KOUAGOU_Ngonga Ngomo_2024, title={Resilience in Knowledge
Graph Embeddings}, DOI={10.48550/ARXIV.2410.21163},
journal={Arxiv}, author={Sharma, Arnab and KOUAGOU, N’Dah Jean and Ngonga Ngomo,
Axel-Cyrille}, year={2024} }'
chicago: Sharma, Arnab, N’Dah Jean KOUAGOU, and Axel-Cyrille Ngonga Ngomo. “Resilience
in Knowledge Graph Embeddings.” Arxiv, 2024. https://doi.org/10.48550/ARXIV.2410.21163.
ieee: 'A. Sharma, N. J. KOUAGOU, and A.-C. Ngonga Ngomo, “Resilience in Knowledge
Graph Embeddings,” Arxiv, 2024, doi: 10.48550/ARXIV.2410.21163.'
mla: Sharma, Arnab, et al. “Resilience in Knowledge Graph Embeddings.” Arxiv,
2024, doi:10.48550/ARXIV.2410.21163.
short: A. Sharma, N.J. KOUAGOU, A.-C. Ngonga Ngomo, Arxiv (2024).
date_created: 2025-01-06T12:19:17Z
date_updated: 2025-01-07T20:01:18Z
doi: 10.48550/ARXIV.2410.21163
language:
- iso: eng
publication: Arxiv
status: public
title: Resilience in Knowledge Graph Embeddings
type: journal_article
user_id: '67200'
year: '2024'
...
---
_id: '55653'
abstract:
- lang: eng
text: We consider the problem of class expression learning using cardinality-minimal
sets of examples. Recent class expression learning approaches employ deep neural
networks and have demonstrated tremendous performance improvements in execution
time and quality of the computed solutions. However, they lack generalization
capabilities when it comes to the number of examples used in a learning problem,
i.e., they often perform poorly on unseen learning problems where only a few examples
are given. In this work, we propose a generalization of the classical class expression
learning problem to address the limitations above. In short, our generalized learning
problem (GLP) forces learning systems to solve the classical class expression
learning problem using the smallest possible subsets of examples, thereby improving
the learning systems' ability to solve unseen learning problems with arbitrary
numbers of examples. Moreover, we develop ROCES, a learning algorithm for synthesis-based
approaches to solve GLP. Experimental results suggest that post training, ROCES
outperforms existing synthesis-based approaches on out-of-distribution learning
problems while remaining highly competitive overall.
author:
- first_name: N'Dah Jean
full_name: KOUAGOU, N'Dah Jean
id: '87189'
last_name: KOUAGOU
- first_name: Stefan
full_name: Heindorf, Stefan
id: '11871'
last_name: Heindorf
orcid: 0000-0002-4525-6865
- first_name: Caglar
full_name: Demir, Caglar
id: '43817'
last_name: Demir
- first_name: Axel-Cyrille
full_name: Ngonga Ngomo, Axel-Cyrille
id: '65716'
last_name: Ngonga Ngomo
citation:
ama: 'KOUAGOU NJ, Heindorf S, Demir C, Ngonga Ngomo A-C. ROCES: Robust Class Expression
Synthesis in Description Logics via Iterative Sampling. In: Proceedings of
the Thirty-ThirdInternational Joint Conference on Artificial Intelligence.
International Joint Conferences on Artificial Intelligence Organization; 2024.
doi:10.24963/ijcai.2024/479'
apa: 'KOUAGOU, N. J., Heindorf, S., Demir, C., & Ngonga Ngomo, A.-C. (2024).
ROCES: Robust Class Expression Synthesis in Description Logics via Iterative Sampling.
Proceedings of the Thirty-ThirdInternational Joint Conference on Artificial
Intelligence. https://doi.org/10.24963/ijcai.2024/479'
bibtex: '@inproceedings{KOUAGOU_Heindorf_Demir_Ngonga Ngomo_2024, title={ROCES:
Robust Class Expression Synthesis in Description Logics via Iterative Sampling},
DOI={10.24963/ijcai.2024/479},
booktitle={Proceedings of the Thirty-ThirdInternational Joint Conference on Artificial
Intelligence}, publisher={International Joint Conferences on Artificial Intelligence
Organization}, author={KOUAGOU, N’Dah Jean and Heindorf, Stefan and Demir, Caglar
and Ngonga Ngomo, Axel-Cyrille}, year={2024} }'
chicago: 'KOUAGOU, N’Dah Jean, Stefan Heindorf, Caglar Demir, and Axel-Cyrille Ngonga
Ngomo. “ROCES: Robust Class Expression Synthesis in Description Logics via Iterative
Sampling.” In Proceedings of the Thirty-ThirdInternational Joint Conference
on Artificial Intelligence. International Joint Conferences on Artificial
Intelligence Organization, 2024. https://doi.org/10.24963/ijcai.2024/479.'
ieee: 'N. J. KOUAGOU, S. Heindorf, C. Demir, and A.-C. Ngonga Ngomo, “ROCES: Robust
Class Expression Synthesis in Description Logics via Iterative Sampling,” 2024,
doi: 10.24963/ijcai.2024/479.'
mla: 'KOUAGOU, N’Dah Jean, et al. “ROCES: Robust Class Expression Synthesis in Description
Logics via Iterative Sampling.” Proceedings of the Thirty-ThirdInternational
Joint Conference on Artificial Intelligence, International Joint Conferences
on Artificial Intelligence Organization, 2024, doi:10.24963/ijcai.2024/479.'
short: 'N.J. KOUAGOU, S. Heindorf, C. Demir, A.-C. Ngonga Ngomo, in: Proceedings
of the Thirty-ThirdInternational Joint Conference on Artificial Intelligence,
International Joint Conferences on Artificial Intelligence Organization, 2024.'
date_created: 2024-08-19T12:43:55Z
date_updated: 2025-07-18T15:52:39Z
ddc:
- '000'
doi: 10.24963/ijcai.2024/479
file:
- access_level: closed
content_type: application/pdf
creator: nkouagou
date_created: 2025-06-26T08:06:07Z
date_updated: 2025-06-26T08:06:07Z
file_id: '60394'
file_name: public.pdf
file_size: 400277
relation: main_file
success: 1
file_date_updated: 2025-06-26T08:06:07Z
has_accepted_license: '1'
language:
- iso: eng
publication: Proceedings of the Thirty-ThirdInternational Joint Conference on Artificial
Intelligence
publication_status: published
publisher: International Joint Conferences on Artificial Intelligence Organization
status: public
title: 'ROCES: Robust Class Expression Synthesis in Description Logics via Iterative
Sampling'
type: conference
user_id: '11871'
year: '2024'
...
---
_id: '46460'
author:
- first_name: Axel-Cyrille
full_name: Ngonga Ngomo, Axel-Cyrille
id: '65716'
last_name: Ngonga Ngomo
- first_name: Caglar
full_name: Demir, Caglar
id: '43817'
last_name: Demir
- first_name: N'Dah Jean
full_name: Kouagou, N'Dah Jean
id: '87189'
last_name: Kouagou
- first_name: Stefan
full_name: Heindorf, Stefan
id: '11871'
last_name: Heindorf
orcid: 0000-0002-4525-6865
- first_name: Nikoloas
full_name: Karalis, Nikoloas
last_name: Karalis
- first_name: Alexander
full_name: Bigerl, Alexander
id: '72857'
last_name: Bigerl
citation:
ama: 'Ngonga Ngomo A-C, Demir C, Kouagou NJ, Heindorf S, Karalis N, Bigerl A. Class
Expression Learning with Multiple Representations. In: Compendium of Neurosymbolic
Artificial Intelligence. IOS Press; 2023:272–286.'
apa: Ngonga Ngomo, A.-C., Demir, C., Kouagou, N. J., Heindorf, S., Karalis, N.,
& Bigerl, A. (2023). Class Expression Learning with Multiple Representations.
In Compendium of Neurosymbolic Artificial Intelligence (pp. 272–286). IOS
Press.
bibtex: '@inbook{Ngonga Ngomo_Demir_Kouagou_Heindorf_Karalis_Bigerl_2023, title={Class
Expression Learning with Multiple Representations}, booktitle={Compendium of Neurosymbolic
Artificial Intelligence}, publisher={IOS Press}, author={Ngonga Ngomo, Axel-Cyrille
and Demir, Caglar and Kouagou, N’Dah Jean and Heindorf, Stefan and Karalis, Nikoloas
and Bigerl, Alexander}, year={2023}, pages={272–286} }'
chicago: Ngonga Ngomo, Axel-Cyrille, Caglar Demir, N’Dah Jean Kouagou, Stefan Heindorf,
Nikoloas Karalis, and Alexander Bigerl. “Class Expression Learning with Multiple
Representations.” In Compendium of Neurosymbolic Artificial Intelligence,
272–286. IOS Press, 2023.
ieee: A.-C. Ngonga Ngomo, C. Demir, N. J. Kouagou, S. Heindorf, N. Karalis, and
A. Bigerl, “Class Expression Learning with Multiple Representations,” in Compendium
of Neurosymbolic Artificial Intelligence, IOS Press, 2023, pp. 272–286.
mla: Ngonga Ngomo, Axel-Cyrille, et al. “Class Expression Learning with Multiple
Representations.” Compendium of Neurosymbolic Artificial Intelligence,
IOS Press, 2023, pp. 272–286.
short: 'A.-C. Ngonga Ngomo, C. Demir, N.J. Kouagou, S. Heindorf, N. Karalis, A.
Bigerl, in: Compendium of Neurosymbolic Artificial Intelligence, IOS Press, 2023,
pp. 272–286.'
date_created: 2023-08-08T11:49:51Z
date_updated: 2023-11-21T08:06:20Z
department:
- _id: '760'
- _id: '574'
language:
- iso: eng
page: 272–286
publication: Compendium of Neurosymbolic Artificial Intelligence
publisher: IOS Press
status: public
title: Class Expression Learning with Multiple Representations
type: book_chapter
user_id: '14931'
year: '2023'
...
---
_id: '47421'
abstract:
- lang: eng
text: Class expression learning in description logics has long been regarded as
an iterative search problem in an infinite conceptual space. Each iteration of
the search process invokes a reasoner and a heuristic function. The reasoner finds
the instances of the current expression, and the heuristic function computes the
information gain and decides on the next step to be taken. As the size of the
background knowledge base grows, search-based approaches for class expression
learning become prohibitively slow. Current neural class expression synthesis
(NCES) approaches investigate the use of neural networks for class expression
learning in the attributive language with complement (ALC). While they show significant
improvements over search-based approaches in runtime and quality of the computed
solutions, they rely on the availability of pretrained embeddings for the input
knowledge base. Moreover, they are not applicable to ontologies in more expressive
description logics. In this paper, we propose a novel NCES approach which extends
the state of the art to the description logic ALCHIQ(D). Our extension, dubbed
NCES2, comes with an improved training data generator and does not require pretrained
embeddings for the input knowledge base as both the embedding model and the class
expression synthesizer are trained jointly. Empirical results on benchmark datasets
suggest that our approach inherits the scalability capability of current NCES
instances with the additional advantage that it supports more complex learning
problems. NCES2 achieves the highest performance overall when compared to search-based
approaches and to its predecessor NCES. We provide our source code, datasets,
and pretrained models at https://github.com/dice-group/NCES2.
author:
- first_name: N'Dah Jean
full_name: Kouagou, N'Dah Jean
id: '87189'
last_name: Kouagou
- first_name: Stefan
full_name: Heindorf, Stefan
id: '11871'
last_name: Heindorf
orcid: 0000-0002-4525-6865
- first_name: Caglar
full_name: Demir, Caglar
id: '43817'
last_name: Demir
- first_name: Axel-Cyrille
full_name: Ngonga Ngomo, Axel-Cyrille
id: '65716'
last_name: Ngonga Ngomo
citation:
ama: 'Kouagou NJ, Heindorf S, Demir C, Ngonga Ngomo A-C. Neural Class Expression
Synthesis in ALCHIQ(D). In: Machine Learning and Knowledge Discovery in Databases:
Research Track. Springer Nature Switzerland; 2023. doi:10.1007/978-3-031-43421-1_12'
apa: 'Kouagou, N. J., Heindorf, S., Demir, C., & Ngonga Ngomo, A.-C. (2023).
Neural Class Expression Synthesis in ALCHIQ(D). In Machine Learning and Knowledge
Discovery in Databases: Research Track. European Conference on Machine Learning
and Principles and Practice of Knowledge Discovery in Databases, Turin. Springer
Nature Switzerland. https://doi.org/10.1007/978-3-031-43421-1_12'
bibtex: '@inbook{Kouagou_Heindorf_Demir_Ngonga Ngomo_2023, place={Cham}, title={Neural
Class Expression Synthesis in ALCHIQ(D)}, DOI={10.1007/978-3-031-43421-1_12},
booktitle={Machine Learning and Knowledge Discovery in Databases: Research Track},
publisher={Springer Nature Switzerland}, author={Kouagou, N’Dah Jean and Heindorf,
Stefan and Demir, Caglar and Ngonga Ngomo, Axel-Cyrille}, year={2023} }'
chicago: 'Kouagou, N’Dah Jean, Stefan Heindorf, Caglar Demir, and Axel-Cyrille Ngonga
Ngomo. “Neural Class Expression Synthesis in ALCHIQ(D).” In Machine Learning
and Knowledge Discovery in Databases: Research Track. Cham: Springer Nature
Switzerland, 2023. https://doi.org/10.1007/978-3-031-43421-1_12.'
ieee: 'N. J. Kouagou, S. Heindorf, C. Demir, and A.-C. Ngonga Ngomo, “Neural Class
Expression Synthesis in ALCHIQ(D),” in Machine Learning and Knowledge Discovery
in Databases: Research Track, Cham: Springer Nature Switzerland, 2023.'
mla: 'Kouagou, N’Dah Jean, et al. “Neural Class Expression Synthesis in ALCHIQ(D).”
Machine Learning and Knowledge Discovery in Databases: Research Track,
Springer Nature Switzerland, 2023, doi:10.1007/978-3-031-43421-1_12.'
short: 'N.J. Kouagou, S. Heindorf, C. Demir, A.-C. Ngonga Ngomo, in: Machine Learning
and Knowledge Discovery in Databases: Research Track, Springer Nature Switzerland,
Cham, 2023.'
conference:
end_date: 2023-09-22
location: Turin
name: European Conference on Machine Learning and Principles and Practice of Knowledge
Discovery in Databases
start_date: 2023-09-18
date_created: 2023-09-25T13:42:01Z
date_updated: 2024-05-22T10:48:24Z
ddc:
- '000'
department:
- _id: '760'
- _id: '574'
doi: 10.1007/978-3-031-43421-1_12
file:
- access_level: open_access
content_type: application/pdf
creator: heindorf
date_created: 2024-05-22T10:45:08Z
date_updated: 2024-05-22T10:46:58Z
file_id: '54417'
file_name: NCES2_public.pdf
file_size: 432708
relation: main_file
file_date_updated: 2024-05-22T10:46:58Z
has_accepted_license: '1'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://papers.dice-research.org/2023/ECML_NCES2/NCES2_public.pdf
oa: '1'
place: Cham
publication: 'Machine Learning and Knowledge Discovery in Databases: Research Track'
publication_identifier:
isbn:
- '9783031434204'
- '9783031434211'
issn:
- 0302-9743
- 1611-3349
publication_status: published
publisher: Springer Nature Switzerland
status: public
title: Neural Class Expression Synthesis in ALCHIQ(D)
type: book_chapter
user_id: '11871'
year: '2023'
...
---
_id: '54612'
author:
- first_name: N'Dah Jean
full_name: KOUAGOU, N'Dah Jean
id: '87189'
last_name: KOUAGOU
- first_name: Stefan
full_name: Heindorf, Stefan
id: '11871'
last_name: Heindorf
orcid: 0000-0002-4525-6865
- first_name: Caglar
full_name: Demir, Caglar
id: '43817'
last_name: Demir
- first_name: Axel-Cyrille
full_name: Ngonga Ngomo, Axel-Cyrille
id: '65716'
last_name: Ngonga Ngomo
citation:
ama: 'KOUAGOU NJ, Heindorf S, Demir C, Ngonga Ngomo A-C. Neural Class Expression
Synthesis (Extended Abstract). In: NeSy 2023, 17th International Workshop on
Neural-Symbolic Learning and Reasoning, Certosa Di Pontignano, Siena, Italy.
CEUR-WS; 2023.'
apa: KOUAGOU, N. J., Heindorf, S., Demir, C., & Ngonga Ngomo, A.-C. (2023).
Neural Class Expression Synthesis (Extended Abstract). NeSy 2023, 17th International
Workshop on Neural-Symbolic Learning and Reasoning, Certosa Di Pontignano, Siena,
Italy.
bibtex: '@inproceedings{KOUAGOU_Heindorf_Demir_Ngonga Ngomo_2023, title={Neural
Class Expression Synthesis (Extended Abstract)}, booktitle={NeSy 2023, 17th International
Workshop on Neural-Symbolic Learning and Reasoning, Certosa di Pontignano, Siena,
Italy}, publisher={CEUR-WS}, author={KOUAGOU, N’Dah Jean and Heindorf, Stefan
and Demir, Caglar and Ngonga Ngomo, Axel-Cyrille}, year={2023} }'
chicago: KOUAGOU, N’Dah Jean, Stefan Heindorf, Caglar Demir, and Axel-Cyrille Ngonga
Ngomo. “Neural Class Expression Synthesis (Extended Abstract).” In NeSy 2023,
17th International Workshop on Neural-Symbolic Learning and Reasoning, Certosa
Di Pontignano, Siena, Italy. CEUR-WS, 2023.
ieee: N. J. KOUAGOU, S. Heindorf, C. Demir, and A.-C. Ngonga Ngomo, “Neural Class
Expression Synthesis (Extended Abstract),” 2023.
mla: KOUAGOU, N’Dah Jean, et al. “Neural Class Expression Synthesis (Extended Abstract).”
NeSy 2023, 17th International Workshop on Neural-Symbolic Learning and Reasoning,
Certosa Di Pontignano, Siena, Italy, CEUR-WS, 2023.
short: 'N.J. KOUAGOU, S. Heindorf, C. Demir, A.-C. Ngonga Ngomo, in: NeSy 2023,
17th International Workshop on Neural-Symbolic Learning and Reasoning, Certosa
Di Pontignano, Siena, Italy, CEUR-WS, 2023.'
date_created: 2024-06-04T15:36:52Z
date_updated: 2024-06-04T15:40:30Z
department:
- _id: '574'
- _id: '760'
keyword:
- 318 SFB-TRR demir dice enexa heindorf knowgraphs kouagou ngonga sail
language:
- iso: eng
publication: NeSy 2023, 17th International Workshop on Neural-Symbolic Learning and
Reasoning, Certosa di Pontignano, Siena, Italy
publisher: CEUR-WS
status: public
title: Neural Class Expression Synthesis (Extended Abstract)
type: conference
user_id: '67199'
year: '2023'
...
---
_id: '33734'
abstract:
- lang: eng
text: 'Many applications require explainable node classification in knowledge graphs.
Towards this end, a popular ``white-box'''' approach is class expression learning:
Given sets of positive and negative nodes, class expressions in description logics
are learned that separate positive from negative nodes. Most existing approaches
are search-based approaches generating many candidate class expressions and selecting
the best one. However, they often take a long time to find suitable class expressions.
In this paper, we cast class expression learning as a translation problem and
propose a new family of class expression learning approaches which we dub neural
class expression synthesizers. Training examples are ``translated'''' into class
expressions in a fashion akin to machine translation. Consequently, our synthesizers
are not subject to the runtime limitations of search-based approaches. We study
three instances of this novel family of approaches based on LSTMs, GRUs, and set
transformers, respectively. An evaluation of our approach on four benchmark datasets
suggests that it can effectively synthesize high-quality class expressions with
respect to the input examples in approximately one second on average. Moreover,
a comparison to state-of-the-art approaches suggests that we achieve better F-measures
on large datasets. For reproducibility purposes, we provide our implementation
as well as pretrained models in our public GitHub repository at https://github.com/dice-group/NeuralClassExpressionSynthesis'
author:
- first_name: N'Dah Jean
full_name: KOUAGOU, N'Dah Jean
id: '87189'
last_name: KOUAGOU
- first_name: Stefan
full_name: Heindorf, Stefan
id: '11871'
last_name: Heindorf
orcid: 0000-0002-4525-6865
- first_name: Caglar
full_name: Demir, Caglar
id: '43817'
last_name: Demir
- first_name: Axel-Cyrille
full_name: Ngonga Ngomo, Axel-Cyrille
id: '65716'
last_name: Ngonga Ngomo
citation:
ama: 'KOUAGOU NJ, Heindorf S, Demir C, Ngonga Ngomo A-C. Neural Class Expression
Synthesis. In: Pesquita C, Jimenez-Ruiz E, McCusker J, et al., eds. The Semantic
Web - 20th Extended Semantic Web Conference (ESWC 2023). Vol 13870. Springer
International Publishing; 2023:209-226. doi:https://doi.org/10.1007/978-3-031-33455-9_13'
apa: KOUAGOU, N. J., Heindorf, S., Demir, C., & Ngonga Ngomo, A.-C. (2023).
Neural Class Expression Synthesis. In C. Pesquita, E. Jimenez-Ruiz, J. McCusker,
D. Faria, M. Dragoni, A. Dimou, R. Troncy, & S. Hertling (Eds.), The Semantic
Web - 20th Extended Semantic Web Conference (ESWC 2023) (Vol. 13870, pp. 209–226).
Springer International Publishing. https://doi.org/10.1007/978-3-031-33455-9_13
bibtex: '@inproceedings{KOUAGOU_Heindorf_Demir_Ngonga Ngomo_2023, title={Neural
Class Expression Synthesis}, volume={13870}, DOI={https://doi.org/10.1007/978-3-031-33455-9_13},
booktitle={The Semantic Web - 20th Extended Semantic Web Conference (ESWC 2023)},
publisher={Springer International Publishing}, author={KOUAGOU, N’Dah Jean and
Heindorf, Stefan and Demir, Caglar and Ngonga Ngomo, Axel-Cyrille}, editor={Pesquita,
Catia and Jimenez-Ruiz, Ernesto and McCusker, Jamie and Faria, Daniel and Dragoni,
Mauro and Dimou, Anastasia and Troncy, Raphael and Hertling, Sven}, year={2023},
pages={209–226} }'
chicago: KOUAGOU, N’Dah Jean, Stefan Heindorf, Caglar Demir, and Axel-Cyrille Ngonga
Ngomo. “Neural Class Expression Synthesis.” In The Semantic Web - 20th Extended
Semantic Web Conference (ESWC 2023), edited by Catia Pesquita, Ernesto Jimenez-Ruiz,
Jamie McCusker, Daniel Faria, Mauro Dragoni, Anastasia Dimou, Raphael Troncy,
and Sven Hertling, 13870:209–26. Springer International Publishing, 2023. https://doi.org/10.1007/978-3-031-33455-9_13.
ieee: 'N. J. KOUAGOU, S. Heindorf, C. Demir, and A.-C. Ngonga Ngomo, “Neural Class
Expression Synthesis,” in The Semantic Web - 20th Extended Semantic Web Conference
(ESWC 2023), Hersonissos, Crete, Greece, 2023, vol. 13870, pp. 209–226, doi:
https://doi.org/10.1007/978-3-031-33455-9_13.'
mla: KOUAGOU, N’Dah Jean, et al. “Neural Class Expression Synthesis.” The Semantic
Web - 20th Extended Semantic Web Conference (ESWC 2023), edited by Catia Pesquita
et al., vol. 13870, Springer International Publishing, 2023, pp. 209–26, doi:https://doi.org/10.1007/978-3-031-33455-9_13.
short: 'N.J. KOUAGOU, S. Heindorf, C. Demir, A.-C. Ngonga Ngomo, in: C. Pesquita,
E. Jimenez-Ruiz, J. McCusker, D. Faria, M. Dragoni, A. Dimou, R. Troncy, S. Hertling
(Eds.), The Semantic Web - 20th Extended Semantic Web Conference (ESWC 2023),
Springer International Publishing, 2023, pp. 209–226.'
conference:
end_date: 2023-06-01
location: Hersonissos, Crete, Greece
name: 20th Extended Semantic Web Conference
start_date: 2023-05-28
date_created: 2022-10-15T19:20:11Z
date_updated: 2023-07-02T18:10:02Z
department:
- _id: '574'
- _id: '760'
doi: https://doi.org/10.1007/978-3-031-33455-9_13
editor:
- first_name: Catia
full_name: Pesquita, Catia
last_name: Pesquita
- first_name: Ernesto
full_name: Jimenez-Ruiz, Ernesto
last_name: Jimenez-Ruiz
- first_name: Jamie
full_name: McCusker, Jamie
last_name: McCusker
- first_name: Daniel
full_name: Faria, Daniel
last_name: Faria
- first_name: Mauro
full_name: Dragoni, Mauro
last_name: Dragoni
- first_name: Anastasia
full_name: Dimou, Anastasia
last_name: Dimou
- first_name: Raphael
full_name: Troncy, Raphael
last_name: Troncy
- first_name: Sven
full_name: Hertling, Sven
last_name: Hertling
external_id:
unknown:
- https://link.springer.com/chapter/10.1007/978-3-031-33455-9_13
intvolume: ' 13870'
keyword:
- Neural network
- Concept learning
- Description logics
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://2023.eswc-conferences.org/wp-content/uploads/2023/05/paper_Kouagou_2023_Neural.pdf
oa: '1'
page: 209 - 226
project:
- _id: '410'
name: 'KnowGraphs: KnowGraphs: Knowledge Graphs at Scale'
- _id: '407'
grant_number: '101070305'
name: 'ENEXA: Efficient Explainable Learning on Knowledge Graphs'
- _id: '285'
grant_number: NW21-059D
name: 'SAIL: SAIL: SustAInable Life-cycle of Intelligent Socio-Technical Systems'
publication: The Semantic Web - 20th Extended Semantic Web Conference (ESWC 2023)
publication_identifier:
unknown:
- 978-3-031-33455-9
publication_status: published
publisher: Springer International Publishing
status: public
title: Neural Class Expression Synthesis
type: conference
user_id: '11871'
volume: 13870
year: '2023'
...
---
_id: '33740'
author:
- first_name: N'Dah Jean
full_name: KOUAGOU, N'Dah Jean
id: '87189'
last_name: KOUAGOU
- first_name: Stefan
full_name: Heindorf, Stefan
id: '11871'
last_name: Heindorf
orcid: 0000-0002-4525-6865
- first_name: Caglar
full_name: Demir, Caglar
id: '43817'
last_name: Demir
- first_name: Axel-Cyrille
full_name: Ngonga Ngomo, Axel-Cyrille
id: '65716'
last_name: Ngonga Ngomo
citation:
ama: 'KOUAGOU NJ, Heindorf S, Demir C, Ngonga Ngomo A-C. Learning Concept Lengths
Accelerates Concept Learning in ALC. In: The Semantic Web. Springer International
Publishing; 2022. doi:10.1007/978-3-031-06981-9_14'
apa: KOUAGOU, N. J., Heindorf, S., Demir, C., & Ngonga Ngomo, A.-C. (2022).
Learning Concept Lengths Accelerates Concept Learning in ALC. In The Semantic
Web. Springer International Publishing. https://doi.org/10.1007/978-3-031-06981-9_14
bibtex: '@inbook{KOUAGOU_Heindorf_Demir_Ngonga Ngomo_2022, place={Cham}, title={Learning
Concept Lengths Accelerates Concept Learning in ALC}, DOI={10.1007/978-3-031-06981-9_14},
booktitle={The Semantic Web}, publisher={Springer International Publishing}, author={KOUAGOU,
N’Dah Jean and Heindorf, Stefan and Demir, Caglar and Ngonga Ngomo, Axel-Cyrille},
year={2022} }'
chicago: 'KOUAGOU, N’Dah Jean, Stefan Heindorf, Caglar Demir, and Axel-Cyrille Ngonga
Ngomo. “Learning Concept Lengths Accelerates Concept Learning in ALC.” In The
Semantic Web. Cham: Springer International Publishing, 2022. https://doi.org/10.1007/978-3-031-06981-9_14.'
ieee: 'N. J. KOUAGOU, S. Heindorf, C. Demir, and A.-C. Ngonga Ngomo, “Learning Concept
Lengths Accelerates Concept Learning in ALC,” in The Semantic Web, Cham:
Springer International Publishing, 2022.'
mla: KOUAGOU, N’Dah Jean, et al. “Learning Concept Lengths Accelerates Concept Learning
in ALC.” The Semantic Web, Springer International Publishing, 2022, doi:10.1007/978-3-031-06981-9_14.
short: 'N.J. KOUAGOU, S. Heindorf, C. Demir, A.-C. Ngonga Ngomo, in: The Semantic
Web, Springer International Publishing, Cham, 2022.'
date_created: 2022-10-15T19:34:41Z
date_updated: 2024-04-03T13:26:10Z
department:
- _id: '574'
- _id: '760'
doi: 10.1007/978-3-031-06981-9_14
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://arxiv.org/abs/2107.04911
oa: '1'
place: Cham
publication: The Semantic Web
publication_identifier:
isbn:
- '9783031069802'
- '9783031069819'
issn:
- 0302-9743
- 1611-3349
publication_status: published
publisher: Springer International Publishing
related_material:
link:
- relation: confirmation
url: https://link.springer.com/chapter/10.1007/978-3-031-06981-9_14
status: public
title: Learning Concept Lengths Accelerates Concept Learning in ALC
type: book_chapter
user_id: '11871'
year: '2022'
...