--- _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: '57240' abstract: - lang: eng text: Validating assertions before adding them to a knowledge graph is an essential part of its creation and maintenance. Due to the sheer size of knowledge graphs, automatic fact-checking approaches have been developed. These approaches rely on reference knowledge to decide whether a given assertion is correct. Recent hybrid approaches achieve good results by including several knowledge sources. However, it is often impractical to provide a sheer quantity of textual knowledge or generate embedding models to leverage these hybrid approaches. We present FaVEL, an approach that uses algorithm selection and ensemble learning to amalgamate several existing fact-checking approaches that rely solely on a reference knowledge graph and, hence, use fewer resources than current hybrid approaches. For our evaluation, we create updated versions of two existing datasets and a new dataset dubbed FaVEL-DS. Our evaluation compares our approach to 15 fact-checking approaches—including the state-of-the-art approach HybridFC—on 3 datasets. Our results demonstrate that FaVEL outperforms all other approaches significantly by at least 0.04 in terms of the area under the ROC curve. Our source code, datasets, and evaluation results are open-source and can be found at https://github.com/dice-group/favel. author: - first_name: Umair full_name: Qudus, Umair id: '83392' last_name: Qudus orcid: 0000-0001-6714-8729 - first_name: Michael full_name: Röder, Michael id: '67199' last_name: Röder orcid: https://orcid.org/0000-0002-8609-8277 - first_name: Franck Lionel full_name: Tatkeu Pekarou, Franck Lionel last_name: Tatkeu Pekarou - first_name: Ana Alexandra full_name: Morim da Silva, Ana Alexandra id: '72108' last_name: Morim da Silva - first_name: Axel-Cyrille full_name: Ngonga Ngomo, Axel-Cyrille id: '65716' last_name: Ngonga Ngomo citation: ama: 'Qudus U, Röder M, Tatkeu Pekarou FL, Morim da Silva AA, Ngonga Ngomo A-C. FaVEL: Fact Validation Ensemble Learning. In: Rospocher M, Mehwish Alam, eds. EKAW 2024. ; 2024.' apa: 'Qudus, U., Röder, M., Tatkeu Pekarou, F. L., Morim da Silva, A. A., & Ngonga Ngomo, A.-C. (2024). FaVEL: Fact Validation Ensemble Learning. In M. Rospocher & Mehwish Alam (Eds.), EKAW 2024.' bibtex: '@inproceedings{Qudus_Röder_Tatkeu Pekarou_Morim da Silva_Ngonga Ngomo_2024, title={FaVEL: Fact Validation Ensemble Learning}, booktitle={EKAW 2024}, author={Qudus, Umair and Röder, Michael and Tatkeu Pekarou, Franck Lionel and Morim da Silva, Ana Alexandra and Ngonga Ngomo, Axel-Cyrille}, editor={Rospocher, Marco and Mehwish Alam}, year={2024} }' chicago: 'Qudus, Umair, Michael Röder, Franck Lionel Tatkeu Pekarou, Ana Alexandra Morim da Silva, and Axel-Cyrille Ngonga Ngomo. “FaVEL: Fact Validation Ensemble Learning.” In EKAW 2024, edited by Marco Rospocher and Mehwish Alam, 2024.' ieee: 'U. Qudus, M. Röder, F. L. Tatkeu Pekarou, A. A. Morim da Silva, and A.-C. Ngonga Ngomo, “FaVEL: Fact Validation Ensemble Learning,” in EKAW 2024, Amsterdam, Netherlands, 2024.' mla: 'Qudus, Umair, et al. “FaVEL: Fact Validation Ensemble Learning.” EKAW 2024, edited by Marco Rospocher and Mehwish Alam, 2024.' short: 'U. Qudus, M. Röder, F.L. Tatkeu Pekarou, A.A. Morim da Silva, A.-C. Ngonga Ngomo, in: M. Rospocher, Mehwish Alam (Eds.), EKAW 2024, 2024.' conference: end_date: 2024-11-28 location: Amsterdam, Netherlands name: 24th International Conference on Knowledge Engineering and Knowledge Management start_date: 2024-11-26 corporate_editor: - Mehwish Alam date_created: 2024-11-19T14:12:49Z date_updated: 2025-09-11T09:48:12Z ddc: - '600' department: - _id: '34' editor: - first_name: Marco full_name: Rospocher, Marco last_name: Rospocher file: - access_level: closed content_type: application/pdf creator: uqudus date_created: 2024-11-19T14:14:14Z date_updated: 2024-11-19T14:14:14Z file_id: '57241' file_name: favel.pdf file_size: 190661 relation: main_file success: 1 file_date_updated: 2024-11-19T14:14:14Z has_accepted_license: '1' keyword: - fact checking - ensemble learning - transfer learning - knowledge management. language: - iso: eng popular_science: '1' project: - _id: '412' name: 'NEBULA: Nutzerzentrierte KI-basierte Erkennung von Fake-News und Fehlinformationen' - _id: '285' name: 'SAIL: SAIL - Nachhaltiger Lebenszyklus von intelligenten soziotechnischen Systemen' - _id: '410' name: 'KnowGraphs: KnowGraphs: Knowledge Graphs at Scale' publication: EKAW 2024 quality_controlled: '1' status: public title: 'FaVEL: Fact Validation Ensemble Learning' type: conference user_id: '83392' year: '2024' ... --- _id: '50479' abstract: - lang: eng text: Verifying assertions is an essential part of creating and maintaining knowledge graphs. Most often, this task cannot be carried out manually due to the sheer size of modern knowledge graphs. Hence, automatic fact-checking approaches have been proposed over the last decade. These approaches aim to compute automatically whether a given assertion is correct or incorrect. However, most fact-checking approaches are binary classifiers that fail to consider the volatility of some assertions, i.e., the fact that such assertions are only valid at certain times or for specific time intervals. Moreover, the few approaches able to predict when an assertion was valid (i.e., time-point prediction approaches) rely on manual feature engineering. This paper presents TEMPORALFC, a temporal fact-checking approach that uses multiple sources of background knowledge to assess the veracity and temporal validity of a given assertion. We evaluate TEMPORALFC on two datasets and compare it to the state of the art in fact-checking and time-point prediction. Our results suggest that TEMPORALFC outperforms the state of the art on the fact-checking task by 0.13 to 0.15 in terms of Area Under the Receiver Operating Characteristic curve and on the time-point prediction task by 0.25 to 0.27 in terms of Mean Reciprocal Rank. Our code is open-source and can be found at https://github.com/dice-group/TemporalFC. author: - first_name: Umair full_name: Qudus, Umair last_name: Qudus - first_name: Michael full_name: Röder, Michael last_name: Röder - first_name: Sabrina full_name: Kirrane, Sabrina last_name: Kirrane - first_name: Axel-Cyrille Ngonga full_name: Ngomo, Axel-Cyrille Ngonga last_name: Ngomo citation: ama: 'Qudus U, Röder M, Kirrane S, Ngomo A-CN. TemporalFC: A Temporal Fact Checking Approach over Knowledge Graphs. In: R. Payne T, Presutti V, Qi G, et al., eds. The Semantic Web – ISWC 2023. Vol 14265. Lecture Notes in Computer Science. Springer, Cham; 2023:465–483. doi:10.1007/978-3-031-47240-4_25' apa: 'Qudus, U., Röder, M., Kirrane, S., & Ngomo, A.-C. N. (2023). TemporalFC: A Temporal Fact Checking Approach over Knowledge Graphs. In T. R. Payne, V. Presutti, G. Qi, M. Poveda-Villalón, G. Stoilos, L. Hollink, Z. Kaoudi, G. Cheng, & J. Li (Eds.), The Semantic Web – ISWC 2023 (Vol. 14265, pp. 465–483). Springer, Cham. https://doi.org/10.1007/978-3-031-47240-4_25' bibtex: '@inproceedings{Qudus_Röder_Kirrane_Ngomo_2023, place={Cham}, series={ Lecture Notes in Computer Science}, title={TemporalFC: A Temporal Fact Checking Approach over Knowledge Graphs}, volume={14265}, DOI={10.1007/978-3-031-47240-4_25}, booktitle={The Semantic Web – ISWC 2023}, publisher={Springer, Cham}, author={Qudus, Umair and Röder, Michael and Kirrane, Sabrina and Ngomo, Axel-Cyrille Ngonga}, editor={R. Payne, Terry and Presutti, Valentina and Qi, Guilin and Poveda-Villalón, María and Stoilos, Giorgos and Hollink, Laura and Kaoudi, Zoi and Cheng, Gong and Li, Juanzi}, year={2023}, pages={465–483}, collection={ Lecture Notes in Computer Science} }' chicago: 'Qudus, Umair, Michael Röder, Sabrina Kirrane, and Axel-Cyrille Ngonga Ngomo. “TemporalFC: A Temporal Fact Checking Approach over Knowledge Graphs.” In The Semantic Web – ISWC 2023, edited by Terry R. Payne, Valentina Presutti, Guilin Qi, María Poveda-Villalón, Giorgos Stoilos, Laura Hollink, Zoi Kaoudi, Gong Cheng, and Juanzi Li, 14265:465–483. Lecture Notes in Computer Science. Cham: Springer, Cham, 2023. https://doi.org/10.1007/978-3-031-47240-4_25.' ieee: 'U. Qudus, M. Röder, S. Kirrane, and A.-C. N. Ngomo, “TemporalFC: A Temporal Fact Checking Approach over Knowledge Graphs,” in The Semantic Web – ISWC 2023, Athens, Greece, 2023, vol. 14265, pp. 465–483, doi: 10.1007/978-3-031-47240-4_25.' mla: 'Qudus, Umair, et al. “TemporalFC: A Temporal Fact Checking Approach over Knowledge Graphs.” The Semantic Web – ISWC 2023, edited by Terry R. Payne et al., vol. 14265, Springer, Cham, 2023, pp. 465–483, doi:10.1007/978-3-031-47240-4_25.' short: 'U. Qudus, M. Röder, S. Kirrane, A.-C.N. Ngomo, in: T. R. Payne, V. Presutti, G. Qi, M. Poveda-Villalón, G. Stoilos, L. Hollink, Z. Kaoudi, G. Cheng, J. Li (Eds.), The Semantic Web – ISWC 2023, Springer, Cham, Cham, 2023, pp. 465–483.' conference: end_date: 2023-11-10 location: Athens, Greece name: The Semantic Web – ISWC 2023 start_date: 2023-11-06 date_created: 2024-01-13T11:22:15Z date_updated: 2024-01-13T11:48:28Z ddc: - '006' department: - _id: '34' doi: 10.1007/978-3-031-47240-4_25 editor: - first_name: Terry full_name: R. Payne, Terry last_name: R. Payne - first_name: Valentina full_name: Presutti, Valentina last_name: Presutti - first_name: Guilin full_name: Qi, Guilin last_name: Qi - first_name: María full_name: Poveda-Villalón, María last_name: Poveda-Villalón - first_name: Giorgos full_name: Stoilos, Giorgos last_name: Stoilos - first_name: Laura full_name: Hollink, Laura last_name: Hollink - first_name: Zoi full_name: Kaoudi, Zoi last_name: Kaoudi - first_name: Gong full_name: Cheng, Gong last_name: Cheng - first_name: Juanzi full_name: Li, Juanzi last_name: Li file: - access_level: closed content_type: application/pdf creator: uqudus date_created: 2024-01-13T11:25:48Z date_updated: 2024-01-13T11:25:48Z file_id: '50480' file_name: ISWC 2023 TemporalFC-A Temporal Fact Checking approach over Knowledge Graphs.pdf file_size: 1944818 relation: main_file success: 1 file_date_updated: 2024-01-13T11:25:48Z has_accepted_license: '1' intvolume: ' 14265' jel: - C keyword: - temporal fact checking · ensemble learning · transfer learning · time-point prediction · temporal knowledge graphs language: - iso: eng page: 465–483 place: Cham project: - _id: '410' grant_number: '860801' name: 'KnowGraphs: KnowGraphs: Knowledge Graphs at Scale' publication: The Semantic Web – ISWC 2023 publication_identifier: isbn: - '9783031472398' - '9783031472404' issn: - 0302-9743 - 1611-3349 publication_status: published publisher: Springer, Cham series_title: ' Lecture Notes in Computer Science' status: public title: 'TemporalFC: A Temporal Fact Checking Approach over Knowledge Graphs' type: conference user_id: '83392' volume: 14265 year: '2023' ... --- _id: '32509' abstract: - lang: eng text: " We consider fact-checking approaches that aim to predict the veracity of assertions in knowledge graphs. Five main categories of fact-checking approaches for knowledge graphs have been proposed in the recent literature, of\r\nwhich each is subject to partially overlapping limitations. In particular, current text-based approaches are limited by manual feature engineering. Path-based and rule-based approaches are limited by their exclusive use of knowledge graphs as background knowledge, and embedding-based approaches suffer from low accuracy scores on current fact-checking tasks. We propose a hybrid approach—dubbed HybridFC—that exploits the diversity of existing categories of fact-checking approaches within an ensemble learning setting to achieve a significantly better prediction performance. In particular, our approach outperforms the state of the art by 0.14 to 0.27 in terms of Area Under the Receiver Operating Characteristic curve on the FactBench dataset. Our code is open-source and can be found at https://github.com/dice-group/HybridFC." author: - first_name: Umair full_name: Qudus, Umair id: '83392' last_name: Qudus orcid: 0000-0001-6714-8729 - first_name: Michael full_name: Röder, Michael id: '67199' last_name: Röder orcid: https://orcid.org/0000-0002-8609-8277 - first_name: Muhammad full_name: Saleem, Muhammad last_name: Saleem - first_name: Axel-Cyrille full_name: Ngonga Ngomo, Axel-Cyrille id: '65716' last_name: Ngonga Ngomo citation: ama: 'Qudus U, Röder M, Saleem M, Ngonga Ngomo A-C. HybridFC: A Hybrid Fact-Checking Approach for Knowledge Graphs. In: Sattler U, Hogan A, Keet M, Presutti V, eds. The Semantic Web -- ISWC 2022. Springer International Publishing; :462--480. doi:10.1007/978-3-031-19433-7_27' apa: 'Qudus, U., Röder, M., Saleem, M., & Ngonga Ngomo, A.-C. (n.d.). HybridFC: A Hybrid Fact-Checking Approach for Knowledge Graphs. In U. Sattler, A. Hogan, M. Keet, & V. Presutti (Eds.), The Semantic Web -- ISWC 2022 (pp. 462--480). Springer International Publishing. https://doi.org/10.1007/978-3-031-19433-7_27' bibtex: '@inproceedings{Qudus_Röder_Saleem_Ngonga Ngomo, place={Cham}, title={HybridFC: A Hybrid Fact-Checking Approach for Knowledge Graphs}, DOI={10.1007/978-3-031-19433-7_27}, booktitle={The Semantic Web -- ISWC 2022}, publisher={Springer International Publishing}, author={Qudus, Umair and Röder, Michael and Saleem, Muhammad and Ngonga Ngomo, Axel-Cyrille}, editor={Sattler, Ulrike and Hogan, Aidan and Keet, Maria and Presutti, Valentina}, pages={462--480} }' chicago: 'Qudus, Umair, Michael Röder, Muhammad Saleem, and Axel-Cyrille Ngonga Ngomo. “HybridFC: A Hybrid Fact-Checking Approach for Knowledge Graphs.” In The Semantic Web -- ISWC 2022, edited by Ulrike Sattler, Aidan Hogan, Maria Keet, and Valentina Presutti, 462--480. Cham: Springer International Publishing, n.d. https://doi.org/10.1007/978-3-031-19433-7_27.' ieee: 'U. Qudus, M. Röder, M. Saleem, and A.-C. Ngonga Ngomo, “HybridFC: A Hybrid Fact-Checking Approach for Knowledge Graphs,” in The Semantic Web -- ISWC 2022, Hanghzou, China, pp. 462--480, doi: 10.1007/978-3-031-19433-7_27.' mla: 'Qudus, Umair, et al. “HybridFC: A Hybrid Fact-Checking Approach for Knowledge Graphs.” The Semantic Web -- ISWC 2022, edited by Ulrike Sattler et al., Springer International Publishing, pp. 462--480, doi:10.1007/978-3-031-19433-7_27.' short: 'U. Qudus, M. Röder, M. Saleem, A.-C. Ngonga Ngomo, in: U. Sattler, A. Hogan, M. Keet, V. Presutti (Eds.), The Semantic Web -- ISWC 2022, Springer International Publishing, Cham, n.d., pp. 462--480.' conference: end_date: 2022-10-27 location: Hanghzou, China name: International Semantic Web Conference (ISWC) start_date: 2022-10-23 date_created: 2022-08-02T11:56:03Z date_updated: 2025-09-11T09:37:16Z ddc: - '000' department: - _id: '34' doi: 10.1007/978-3-031-19433-7_27 editor: - first_name: Ulrike full_name: Sattler, Ulrike last_name: Sattler - first_name: Aidan full_name: Hogan, Aidan last_name: Hogan - first_name: Maria full_name: Keet, Maria last_name: Keet - first_name: Valentina full_name: Presutti, Valentina last_name: Presutti file: - access_level: closed content_type: application/pdf creator: uqudus date_created: 2022-12-22T15:45:29Z date_updated: 2022-12-22T15:45:29Z file_id: '34853' file_name: hybrid_fact_check_iswc2022.pdf file_size: 296218 relation: main_file success: 1 file_date_updated: 2022-12-22T15:45:29Z has_accepted_license: '1' keyword: - fact checking · ensemble learning · knowledge graph veracit language: - iso: eng page: 462--480 place: Cham popular_science: '1' project: - _id: '410' name: 'KnowGraphs: KnowGraphs: Knowledge Graphs at Scale' publication: The Semantic Web -- ISWC 2022 publication_identifier: isbn: - 978-3-031-19433-7 publication_status: accepted publisher: Springer International Publishing quality_controlled: '1' status: public title: 'HybridFC: A Hybrid Fact-Checking Approach for Knowledge Graphs' type: conference user_id: '83392' year: '2022' ...