← Search

Nicola Di Mauro

2 accepted papers

2023

How to Turn Your Knowledge Graph Embeddings into Generative Models

NeurIPS 2023oral

Some of the most successful knowledge graph embedding (KGE) models for link prediction – CP, RESCAL, TuckER, ComplEx – can be interpreted as energy-based models. Under this perspective they are not amenable for exact maximum-likelihood estimation (MLE), sampling and struggle to integrate logical con…