Domain and Range Aware Synthetic Negatives Generation for Knowledge Graph Embedding Models

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Bernardi, Alberto, Costabello, Luca
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916492197494784
author Bernardi, Alberto
Costabello, Luca
author_facet Bernardi, Alberto
Costabello, Luca
contents Knowledge Graph Embedding models, representing entities and edges in a low-dimensional space, have been extremely successful at solving tasks related to completing and exploring Knowledge Graphs (KGs). One of the key aspects of training most of these models is teaching to discriminate between true statements positives and false ones (negatives). However, the way in which negatives can be defined is not trivial, as facts missing from the KG are not necessarily false and a set of ground truth negatives is hardly ever given. This makes synthetic negative generation a necessity. Different generation strategies can heavily affect the quality of the embeddings, making it a primary aspect to consider. We revamp a strategy that generates corruptions during training respecting the domain and range of relations, we extend its capabilities and we show our methods bring substantial improvement (+10% MRR) for standard benchmark datasets and over +150% MRR for a larger ontology-backed dataset.
format Preprint
id arxiv_https___arxiv_org_abs_2411_14858
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Domain and Range Aware Synthetic Negatives Generation for Knowledge Graph Embedding Models
Bernardi, Alberto
Costabello, Luca
Artificial Intelligence
Knowledge Graph Embedding models, representing entities and edges in a low-dimensional space, have been extremely successful at solving tasks related to completing and exploring Knowledge Graphs (KGs). One of the key aspects of training most of these models is teaching to discriminate between true statements positives and false ones (negatives). However, the way in which negatives can be defined is not trivial, as facts missing from the KG are not necessarily false and a set of ground truth negatives is hardly ever given. This makes synthetic negative generation a necessity. Different generation strategies can heavily affect the quality of the embeddings, making it a primary aspect to consider. We revamp a strategy that generates corruptions during training respecting the domain and range of relations, we extend its capabilities and we show our methods bring substantial improvement (+10% MRR) for standard benchmark datasets and over +150% MRR for a larger ontology-backed dataset.
title Domain and Range Aware Synthetic Negatives Generation for Knowledge Graph Embedding Models
topic Artificial Intelligence
url https://arxiv.org/abs/2411.14858