Parameter Averaging in Link Prediction

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.

Download
OA public.pdf 837.46 KB
Conference Paper | English
Author
Sapkota, RupeshLibreCat; Demir, Caglar; Sharma, Arnab; Ngonga Ngomo, Axel-Cyrille
Abstract
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 KGE 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.
Publishing Year
Proceedings Title
Proceedings of the Thirteenth International Conference on Knowledge Capture(K-CAP 2025)
Conference
Knowledge Capture Conference 2025
Conference Location
Dayton, OH, USA
Conference Date
2025-12-10 – 2025-12-10
LibreCat-ID

Cite this

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
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
@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} }
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.
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.
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.
All files available under the following license(s):
Copyright Statement:
This Item is protected by copyright and/or related rights. [...]
Main File(s)
File Name
public.pdf 837.46 KB
Access Level
OA Open Access
Last Uploaded
2025-10-28T10:02:13Z


Link(s) to Main File(s)
Access Level
Restricted Closed Access

Export

Marked Publications

Open Data LibreCat

Search this title in

Google Scholar