---
_id: '62007'
abstract:
- lang: eng
text: "Ensemble methods are widely employed to improve generalization in machine
learning. This has also prompted the adoption of ensemble learning for the knowledge
graph embedding (KGE) models in performing link prediction. Typical approaches
to this end train multiple models as part of the ensemble, and the diverse predictions
are then averaged. However, this approach has some significant drawbacks. For
instance, the computational overhead of training multiple models increases latency
and memory overhead. In contrast, model merging approaches offer a promising alternative
that does not require training multiple models. In this work, we introduce model
merging, specifically weighted averaging, in\r\nKGE models. Herein, a running
average of model parameters from a training epoch onward is maintained and used
for predictions. To address this, we additionally propose an approach that selectively
updates the running average of the ensemble model parameters only when the generalization
performance improves on a validation dataset. We evaluate these two different
weighted averaging approaches on link prediction tasks, comparing the state-of-the-art
benchmark ensemble approach. Additionally, we evaluate the weighted averaging
approach considering literal-augmented KGE models and multi-hop query answering
tasks as well. The results demonstrate that the proposed weighted averaging approach
consistently improves performance across diverse evaluation settings."
author:
- first_name: Rupesh
full_name: Sapkota, Rupesh
id: '89326'
last_name: Sapkota
- first_name: Caglar
full_name: Demir, Caglar
last_name: Demir
- first_name: Arnab
full_name: Sharma, Arnab
last_name: Sharma
- first_name: Axel-Cyrille
full_name: Ngonga Ngomo, Axel-Cyrille
last_name: Ngonga Ngomo
citation:
ama: 'Sapkota R, Demir C, Sharma A, Ngonga Ngomo A-C. Parameter Averaging in Link
Prediction. In: Proceedings of the Thirteenth International Conference on Knowledge
Capture(K-CAP 2025). ACM; 2025. doi:https://doi.org/10.1145/3731443.3771365'
apa: Sapkota, R., Demir, C., Sharma, A., & Ngonga Ngomo, A.-C. (2025). Parameter
Averaging in Link Prediction. Proceedings of the Thirteenth International Conference
on Knowledge Capture(K-CAP 2025). Knowledge Capture Conference 2025, Dayton,
OH, USA. https://doi.org/10.1145/3731443.3771365
bibtex: '@inproceedings{Sapkota_Demir_Sharma_Ngonga Ngomo_2025, place={Dayton, OH,
USA}, title={Parameter Averaging in Link Prediction}, DOI={https://doi.org/10.1145/3731443.3771365},
booktitle={Proceedings of the Thirteenth International Conference on Knowledge
Capture(K-CAP 2025)}, publisher={ACM}, author={Sapkota, Rupesh and Demir, Caglar
and Sharma, Arnab and Ngonga Ngomo, Axel-Cyrille}, year={2025} }'
chicago: 'Sapkota, Rupesh, Caglar Demir, Arnab Sharma, and Axel-Cyrille Ngonga Ngomo.
“Parameter Averaging in Link Prediction.” In Proceedings of the Thirteenth
International Conference on Knowledge Capture(K-CAP 2025). Dayton, OH, USA:
ACM, 2025. https://doi.org/10.1145/3731443.3771365.'
ieee: 'R. Sapkota, C. Demir, A. Sharma, and A.-C. Ngonga Ngomo, “Parameter Averaging
in Link Prediction,” presented at the Knowledge Capture Conference 2025, Dayton,
OH, USA, 2025, doi: https://doi.org/10.1145/3731443.3771365.'
mla: Sapkota, Rupesh, et al. “Parameter Averaging in Link Prediction.” Proceedings
of the Thirteenth International Conference on Knowledge Capture(K-CAP 2025),
ACM, 2025, doi:https://doi.org/10.1145/3731443.3771365.
short: 'R. Sapkota, C. Demir, A. Sharma, A.-C. Ngonga Ngomo, in: Proceedings of
the Thirteenth International Conference on Knowledge Capture(K-CAP 2025), ACM,
Dayton, OH, USA, 2025.'
conference:
end_date: 2025-12-10
location: Dayton, OH, USA
name: Knowledge Capture Conference 2025
start_date: 2025-12-10
date_created: 2025-10-28T10:02:40Z
date_updated: 2025-12-04T09:15:07Z
ddc:
- '000'
department:
- _id: '574'
doi: https://doi.org/10.1145/3731443.3771365
file:
- access_level: open_access
content_type: application/pdf
creator: rupezzz
date_created: 2025-10-28T10:02:13Z
date_updated: 2025-10-28T10:02:13Z
file_id: '62008'
file_name: public.pdf
file_size: 837462
relation: main_file
file_date_updated: 2025-10-28T10:02:13Z
has_accepted_license: '1'
keyword:
- Knowledge Graphs
- Embeddings
- Ensemble Learning
language:
- iso: eng
main_file_link:
- url: https://papers.dice-research.org/2025/KCAP_ASWA/public.pdf
oa: '1'
place: Dayton, OH, USA
project:
- _id: '285'
name: SAIL - Nachhaltiger Lebenszyklus von intelligenten soziotechnischen Systemen
publication: Proceedings of the Thirteenth International Conference on Knowledge Capture(K-CAP
2025)
publisher: ACM
status: public
title: Parameter Averaging in Link Prediction
type: conference
user_id: '89326'
year: '2025'
...
---
_id: '56213'
author:
- first_name: Rupesh
full_name: Sapkota, Rupesh
id: '89326'
last_name: Sapkota
- first_name: Dominik
full_name: Köhler, Dominik
last_name: Köhler
- first_name: Stefan
full_name: Heindorf, Stefan
id: '11871'
last_name: Heindorf
orcid: 0000-0002-4525-6865
citation:
ama: 'Sapkota R, Köhler D, Heindorf S. EDGE: Evaluation Framework for Logical vs.
Subgraph Explanations for Node Classifiers on Knowledge Graphs. In: Proceedings
of the 33rd ACM International Conference on Information and Knowledge Management
(CIKM ’24),. ACM; 2024. doi:10.1145/3627673.3679904'
apa: 'Sapkota, R., Köhler, D., & Heindorf, S. (2024). EDGE: Evaluation Framework
for Logical vs. Subgraph Explanations for Node Classifiers on Knowledge Graphs.
Proceedings of the 33rd ACM International Conference on Information and Knowledge
Management (CIKM ’24),. 33rd ACM International Conference on Information and
Knowledge Management, Boise, Idaho, USA. https://doi.org/10.1145/3627673.3679904'
bibtex: '@inproceedings{Sapkota_Köhler_Heindorf_2024, place={Boise, Idaho, USA},
title={EDGE: Evaluation Framework for Logical vs. Subgraph Explanations for Node
Classifiers on Knowledge Graphs}, DOI={10.1145/3627673.3679904},
booktitle={Proceedings of the 33rd ACM International Conference on Information
and Knowledge Management (CIKM ’24),}, publisher={ACM}, author={Sapkota, Rupesh
and Köhler, Dominik and Heindorf, Stefan}, year={2024} }'
chicago: 'Sapkota, Rupesh, Dominik Köhler, and Stefan Heindorf. “EDGE: Evaluation
Framework for Logical vs. Subgraph Explanations for Node Classifiers on Knowledge
Graphs.” In Proceedings of the 33rd ACM International Conference on Information
and Knowledge Management (CIKM ’24),. Boise, Idaho, USA: ACM, 2024. https://doi.org/10.1145/3627673.3679904.'
ieee: 'R. Sapkota, D. Köhler, and S. Heindorf, “EDGE: Evaluation Framework for Logical
vs. Subgraph Explanations for Node Classifiers on Knowledge Graphs,” presented
at the 33rd ACM International Conference on Information and Knowledge Management,
Boise, Idaho, USA, 2024, doi: 10.1145/3627673.3679904.'
mla: 'Sapkota, Rupesh, et al. “EDGE: Evaluation Framework for Logical vs. Subgraph
Explanations for Node Classifiers on Knowledge Graphs.” Proceedings of the
33rd ACM International Conference on Information and Knowledge Management (CIKM
’24), ACM, 2024, doi:10.1145/3627673.3679904.'
short: 'R. Sapkota, D. Köhler, S. Heindorf, in: Proceedings of the 33rd ACM International
Conference on Information and Knowledge Management (CIKM ’24), ACM, Boise, Idaho,
USA, 2024.'
conference:
end_date: 2024-10-25
location: Boise, Idaho, USA
name: 33rd ACM International Conference on Information and Knowledge Management
start_date: 2024-10-21
date_created: 2024-09-23T12:30:10Z
date_updated: 2024-09-23T12:30:25Z
department:
- _id: '760'
- _id: '574'
doi: 10.1145/3627673.3679904
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://papers.dice-research.org/2024/CIKM_EDGE/public.pdf
oa: '1'
place: Boise, Idaho, USA
project:
- _id: '285'
grant_number: NW21-059D
name: 'SAIL: SAIL - Nachhaltiger Lebenszyklus von intelligenten soziotechnischen
Systemen'
publication: Proceedings of the 33rd ACM International Conference on Information and
Knowledge Management (CIKM ’24),
publisher: ACM
status: public
title: 'EDGE: Evaluation Framework for Logical vs. Subgraph Explanations for Node
Classifiers on Knowledge Graphs'
type: conference
user_id: '11871'
year: '2024'
...