Neural Methods for Logical Reasoning Over Knowledge Graphs
| Autor: | Amayuelas, Alfonso, Zhang, Shuai, Rao, Susie Xi, Zhang, Ce |
|---|---|
| Rok vydání: | 2022 |
| Předmět: | |
| Zdroj: | International Conference on Learning Representations, 2022 |
| Druh dokumentu: | Working Paper |
| Popis: | Reasoning is a fundamental problem for computers and deeply studied in Artificial Intelligence. In this paper, we specifically focus on answering multi-hop logical queries on Knowledge Graphs (KGs). This is a complicated task because, in real-world scenarios, the graphs tend to be large and incomplete. Most previous works have been unable to create models that accept full First-Order Logical (FOL) queries, which include negative queries, and have only been able to process a limited set of query structures. Additionally, most methods present logic operators that can only perform the logical operation they are made for. We introduce a set of models that use Neural Networks to create one-point vector embeddings to answer the queries. The versatility of neural networks allows the framework to handle FOL queries with Conjunction ($\wedge$), Disjunction ($\vee$) and Negation ($\neg$) operators. We demonstrate experimentally the performance of our model through extensive experimentation on well-known benchmarking datasets. Besides having more versatile operators, the models achieve a 10\% relative increase over the best performing state of the art and more than 30\% over the original method based on single-point vector embeddings. Comment: 14 pages, 5 figures, 11 tables |
| Databáze: | arXiv |
| Externí odkaz: |
|