One Model, Any Conjunctive Query: Graph Neural Networks for Answering Queries over Incomplete Knowledge Graphs

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Olejniczak, Krzysztof, Huang, Xingyue, Galkin, Mikhail, Ceylan, İsmail İlkan
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914290261295104
author Olejniczak, Krzysztof
Huang, Xingyue
Galkin, Mikhail
Ceylan, İsmail İlkan
author_facet Olejniczak, Krzysztof
Huang, Xingyue
Galkin, Mikhail
Ceylan, İsmail İlkan
contents Motivated by the incompleteness of modern knowledge graphs, a new setup for query answering has emerged, where the goal is to predict answers that do not necessarily appear in the knowledge graph, but are present in its completion. In this paper, we formally introduce and study two query answering problems, namely, query answer classification and query answer retrieval. To solve these problems, we propose AnyCQ, a model that can classify answers to any conjunctive query on any knowledge graph. At the core of our framework lies a graph neural network trained using a reinforcement learning objective to answer Boolean queries. Trained only on simple, small instances, AnyCQ generalizes to large queries of arbitrary structure, reliably classifying and retrieving answers to queries that existing approaches fail to handle. This is empirically validated through our newly proposed, challenging benchmarks. Finally, we empirically show that AnyCQ can effectively transfer to completely novel knowledge graphs when equipped with an appropriate link prediction model, highlighting its potential for querying incomplete data.
format Preprint
id arxiv_https___arxiv_org_abs_2409_13959
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle One Model, Any Conjunctive Query: Graph Neural Networks for Answering Queries over Incomplete Knowledge Graphs
Olejniczak, Krzysztof
Huang, Xingyue
Galkin, Mikhail
Ceylan, İsmail İlkan
Machine Learning
Artificial Intelligence
Motivated by the incompleteness of modern knowledge graphs, a new setup for query answering has emerged, where the goal is to predict answers that do not necessarily appear in the knowledge graph, but are present in its completion. In this paper, we formally introduce and study two query answering problems, namely, query answer classification and query answer retrieval. To solve these problems, we propose AnyCQ, a model that can classify answers to any conjunctive query on any knowledge graph. At the core of our framework lies a graph neural network trained using a reinforcement learning objective to answer Boolean queries. Trained only on simple, small instances, AnyCQ generalizes to large queries of arbitrary structure, reliably classifying and retrieving answers to queries that existing approaches fail to handle. This is empirically validated through our newly proposed, challenging benchmarks. Finally, we empirically show that AnyCQ can effectively transfer to completely novel knowledge graphs when equipped with an appropriate link prediction model, highlighting its potential for querying incomplete data.
title One Model, Any Conjunctive Query: Graph Neural Networks for Answering Queries over Incomplete Knowledge Graphs
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2409.13959