Résumé
More and more often ML models are criticised for their lack of interpretability. One must be able to understand the decision process of the model that led to the refusal of its mortgage, the diagnosis of a disease, or any legal advice.The ability to provide an explanation for a prediction is crucial and has been in the spotlight for a moment now.
Link prediction is an interesting task among the knowledge graph realm due to its various applications, \textit{e.g.} user recommendation, fact-checking, \textit{etc}.
As far as we know, the methods providing the best results for link prediction are based on embeddings, and therefore are not intrinsically comprehensible by a human.
This work proposes a post-hoc interpretability procedure based on rule mining that retrieves some insights about the models' motivations for the provided predictions.
| la date de réponse | 1 sept. 2021 |
|---|---|
| langue originale | Anglais |
| L'institution diplômante |
|
| Superviseur | Benoît Frénay (Promoteur) |