Link Prediction methods aim at predicting missing facts in Knowledge Graphs (KGs) as they are inherently incomplete. Several methods rely on Knowledge Graph Embeddings, which are numerical representations of elements in the Knowledge Graph. Embeddings are effective and scalable for large KGs; however, they lack explainability.Kelpie is a recent and versatile framework that provides post-hoc explanations for predictions based on embeddings by revealing the facts that enabled them. Problems have been recognized, however, with filtering potential explanations and dealing with an overload of candidates. We aim at enhancing Kelpie by targeting three goals: reducing the number of candidates, producing explanations at different levels of detail, and improving the effectiveness of the explanations. To accomplish them, we adopt a semantic similarity measure to enhance the filtering of potential explanations, and we focus on a condensed representation of the search space in the form of a quotient graph based on entity types. Three quotient formulations of different granularity are considered to reduce the risk of losing valuable information. We conduct a quantitative and qualitative experimental evaluation of the proposed solutions, using Kelpie as a baseline.
Explanation of Link Predictions on Knowledge Graphs via Levelwise Filtering and Graph Summarization
Roberto Barile
;Claudia d'Amato
;Nicola Fanizzi
2024-01-01
Abstract
Link Prediction methods aim at predicting missing facts in Knowledge Graphs (KGs) as they are inherently incomplete. Several methods rely on Knowledge Graph Embeddings, which are numerical representations of elements in the Knowledge Graph. Embeddings are effective and scalable for large KGs; however, they lack explainability.Kelpie is a recent and versatile framework that provides post-hoc explanations for predictions based on embeddings by revealing the facts that enabled them. Problems have been recognized, however, with filtering potential explanations and dealing with an overload of candidates. We aim at enhancing Kelpie by targeting three goals: reducing the number of candidates, producing explanations at different levels of detail, and improving the effectiveness of the explanations. To accomplish them, we adopt a semantic similarity measure to enhance the filtering of potential explanations, and we focus on a condensed representation of the search space in the form of a quotient graph based on entity types. Three quotient formulations of different granularity are considered to reduce the risk of losing valuable information. We conduct a quantitative and qualitative experimental evaluation of the proposed solutions, using Kelpie as a baseline.File | Dimensione | Formato | |
---|---|---|---|
ESWC_2024___Paper___Camready-1.pdf
accesso aperto
Tipologia:
Documento in Post-print
Licenza:
Creative commons
Dimensione
410.31 kB
Formato
Adobe PDF
|
410.31 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.