A*Net and NBFNet Learn Negative Patterns on Knowledge Graphs
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917859755556864 |
|---|---|
| author | Betz, Patrick Stelzner, Nathanael Meilicke, Christian Stuckenschmidt, Heiner Bartelt, Christian |
| author_facet | Betz, Patrick Stelzner, Nathanael Meilicke, Christian Stuckenschmidt, Heiner Bartelt, Christian |
| contents | In this technical report, we investigate the predictive performance differences of a rule-based approach and the GNN architectures NBFNet and A*Net with respect to knowledge graph completion. For the two most common benchmarks, we find that a substantial fraction of the performance difference can be explained by one unique negative pattern on each dataset that is hidden from the rule-based approach. Our findings add a unique perspective on the performance difference of different model classes for knowledge graph completion: Models can achieve a predictive performance advantage by penalizing scores of incorrect facts opposed to providing high scores for correct facts. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_05114 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A*Net and NBFNet Learn Negative Patterns on Knowledge Graphs Betz, Patrick Stelzner, Nathanael Meilicke, Christian Stuckenschmidt, Heiner Bartelt, Christian Artificial Intelligence In this technical report, we investigate the predictive performance differences of a rule-based approach and the GNN architectures NBFNet and A*Net with respect to knowledge graph completion. For the two most common benchmarks, we find that a substantial fraction of the performance difference can be explained by one unique negative pattern on each dataset that is hidden from the rule-based approach. Our findings add a unique perspective on the performance difference of different model classes for knowledge graph completion: Models can achieve a predictive performance advantage by penalizing scores of incorrect facts opposed to providing high scores for correct facts. |
| title | A*Net and NBFNet Learn Negative Patterns on Knowledge Graphs |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2412.05114 |