Kelpie: an explainability framework for embedding-based link prediction models

The latest generations of Link Prediction (LP) models rely on embeddings to tackle incompleteness in Knowledge Graphs, achieving great performance at the cost of interpretability. Their opaqueness limits the trust that users can place in them, hindering their adoption in real-world applications. We...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings of the VLDB Endowment 2022-08, Vol.15 (12), p.3566-3569
Main Authors: Rossi, Andrea, Firmani, Donatella, Merialdo, Paolo, Teofili, Tommaso
Format: Article
Language:English
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The latest generations of Link Prediction (LP) models rely on embeddings to tackle incompleteness in Knowledge Graphs, achieving great performance at the cost of interpretability. Their opaqueness limits the trust that users can place in them, hindering their adoption in real-world applications. We have recently introduced Kelpie, an explainability framework tailored specifically for embedding-based LP models. Kelpie can be applied to any embedding-based LP model, and supports two explanation scenarios that we have called necessary and sufficient. In this demonstration we showcase Kelpie's capability to explain the predictions of models based on vastly different architectures on the 5 major datasets in literature.
ISSN:2150-8097
2150-8097
DOI:10.14778/3554821.3554845