Reevaluation of Inductive Link Prediction
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_ | 1866909330562875392 |
|---|---|
| author | Ott, Simon Meilicke, Christian Stuckenschmidt, Heiner |
| author_facet | Ott, Simon Meilicke, Christian Stuckenschmidt, Heiner |
| contents | Within this paper, we show that the evaluation protocol currently used for inductive link prediction is heavily flawed as it relies on ranking the true entity in a small set of randomly sampled negative entities. Due to the limited size of the set of negatives, a simple rule-based baseline can achieve state-of-the-art results, which simply ranks entities higher based on the validity of their type. As a consequence of these insights, we reevaluate current approaches for inductive link prediction on several benchmarks using the link prediction protocol usually applied to the transductive setting. As some inductive methods suffer from scalability issues when evaluated in this setting, we propose and apply additionally an improved sampling protocol, which does not suffer from the problem mentioned above. The results of our evaluation differ drastically from the results reported in so far. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_20130 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Reevaluation of Inductive Link Prediction Ott, Simon Meilicke, Christian Stuckenschmidt, Heiner Artificial Intelligence Machine Learning Within this paper, we show that the evaluation protocol currently used for inductive link prediction is heavily flawed as it relies on ranking the true entity in a small set of randomly sampled negative entities. Due to the limited size of the set of negatives, a simple rule-based baseline can achieve state-of-the-art results, which simply ranks entities higher based on the validity of their type. As a consequence of these insights, we reevaluate current approaches for inductive link prediction on several benchmarks using the link prediction protocol usually applied to the transductive setting. As some inductive methods suffer from scalability issues when evaluated in this setting, we propose and apply additionally an improved sampling protocol, which does not suffer from the problem mentioned above. The results of our evaluation differ drastically from the results reported in so far. |
| title | Reevaluation of Inductive Link Prediction |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2409.20130 |