Efficient embeddings of logical variables for query answering over incomplete knowledge graphs
The problem of answering complex First-order Logic queries over incomplete knowledge graphs is receiving growing attention in the literature. A promising recent approach to this problem has been to exploit neural link predictors, which can be effective in identifying individual missing triples in th...
| Main Authors: | , , |
|---|---|
| Format: | Conference item |
| Language: | English |
| Published: |
Association for the Advancement of Artificial Intelligence
2023
|
| _version_ | 1797110941227155456 |
|---|---|
| author | Wang, D Chen, Y Cuenca Grau, B |
| author_facet | Wang, D Chen, Y Cuenca Grau, B |
| author_sort | Wang, D |
| collection | OXFORD |
| description | The problem of answering complex First-order Logic queries over incomplete knowledge graphs is receiving growing attention in the literature. A promising recent approach to this problem has been to exploit neural link predictors, which can be effective in identifying individual missing triples in the incomplete graph, in order to efficiently answer complex queries. A crucial advantage of this approach over other methods is that it does not require example answers to complex queries for training, as it relies only on the availability of a trained link predictor for the knowledge graph at hand. This approach, however, can be computationally expensive during inference, and cannot deal with queries involving negation. In this paper, we propose a novel approach that addresses all of these limitations. Experiments on established benchmark datasets demonstrate that our approach offers superior performance while significantly reducing inference times. |
| first_indexed | 2024-03-07T08:01:39Z |
| format | Conference item |
| id | oxford-uuid:27c9b239-20d0-449f-b425-b5065eb128fe |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-07T08:01:39Z |
| publishDate | 2023 |
| publisher | Association for the Advancement of Artificial Intelligence |
| record_format | dspace |
| spelling | oxford-uuid:27c9b239-20d0-449f-b425-b5065eb128fe2023-10-11T10:52:38ZEfficient embeddings of logical variables for query answering over incomplete knowledge graphsConference itemhttp://purl.org/coar/resource_type/c_5794uuid:27c9b239-20d0-449f-b425-b5065eb128feEnglishSymplectic Elements Association for the Advancement of Artificial Intelligence2023Wang, DChen, YCuenca Grau, BThe problem of answering complex First-order Logic queries over incomplete knowledge graphs is receiving growing attention in the literature. A promising recent approach to this problem has been to exploit neural link predictors, which can be effective in identifying individual missing triples in the incomplete graph, in order to efficiently answer complex queries. A crucial advantage of this approach over other methods is that it does not require example answers to complex queries for training, as it relies only on the availability of a trained link predictor for the knowledge graph at hand. This approach, however, can be computationally expensive during inference, and cannot deal with queries involving negation. In this paper, we propose a novel approach that addresses all of these limitations. Experiments on established benchmark datasets demonstrate that our approach offers superior performance while significantly reducing inference times. |
| spellingShingle | Wang, D Chen, Y Cuenca Grau, B Efficient embeddings of logical variables for query answering over incomplete knowledge graphs |
| title | Efficient embeddings of logical variables for query answering over incomplete knowledge graphs |
| title_full | Efficient embeddings of logical variables for query answering over incomplete knowledge graphs |
| title_fullStr | Efficient embeddings of logical variables for query answering over incomplete knowledge graphs |
| title_full_unstemmed | Efficient embeddings of logical variables for query answering over incomplete knowledge graphs |
| title_short | Efficient embeddings of logical variables for query answering over incomplete knowledge graphs |
| title_sort | efficient embeddings of logical variables for query answering over incomplete knowledge graphs |
| work_keys_str_mv | AT wangd efficientembeddingsoflogicalvariablesforqueryansweringoverincompleteknowledgegraphs AT cheny efficientembeddingsoflogicalvariablesforqueryansweringoverincompleteknowledgegraphs AT cuencagraub efficientembeddingsoflogicalvariablesforqueryansweringoverincompleteknowledgegraphs |