Query2box: Reasoning over Knowledge Graphs in Vector Space using Box Embeddings

Abstract

Answering complex logical queries on large-scale incomplete knowledge graphs (KGs) is a fundamental yet challenging task. Recently, a promising approach to this problem has been to embed KG entities as well as the query into a vector space such that entities that answer the query are embedded close to the query. However, prior work models queries as single points in the vector space, which is problematic because a complex query represents a potentially large set of its answer entities, but it is unclear how such a set can be represented as a single point. Furthermore, prior work can only handle queries that use conjunctions ($\wedge$) and existential quantifiers ($\exists$). Handling queries with logical disjunctions ($\vee$) remains an open problem. Here we propose query2box, an embedding-based framework for reasoning over arbitrary queries with $\wedge$, $\vee$, and $\exists$ operators in massive and incomplete KGs. Our main insight is that queries can be embedded as boxes (i.e., hyper-rectangles), where a set of points inside the box corresponds to a set of answer entities of the query. We show that conjunctions can be naturally represented as intersections of boxes and also prove a negative result that handling disjunctions would require embedding with dimension proportional to the number of KG entities. However, we show that by transforming queries into a Disjunctive Normal Form, query2box is capable of handling arbitrary logical queries with $\wedge$, $\vee$, $\exists$ in a scalable manner. We demonstrate the effectiveness of query2box on three large KGs and show that query2box achieves up to 25% relative improvement over the state of the art.

ICLR 2020

References in corpus (2)

• RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space
• Improved Representation Learning for Predicting Commonsense Ontologies

Cited by in corpus (13)

• Facts as Experts: Adaptable and Interpretable Neural Memory over Symbolic Knowledge
• Improving Local Identifiability in Probabilistic Box Embeddings
• Complex Query Answering with Neural Link Predictors
• Role-Aware Modeling for N-ary Relational Knowledge Bases
• Logic Embeddings for Complex Query Answering
• SMORE: Knowledge Graph Completion and Multi-hop Reasoning in Massive Knowledge Graphs
• Probabilistic Entity Representation Model for Reasoning over Knowledge Graphs
• Benchmarking the Combinatorial Generalizability of Complex Query Answering on Knowledge Graphs
• Learning Syllogism with Euler Neural-Networks
• Towards Robust Reasoning over Knowledge Graphs
• SQALER: Scaling Question Answering by Decoupling Multi-Hop and Logical Reasoning
• Learning User Representations with Hypercuboids for Recommender Systems
• LNN-EL: A Neuro-Symbolic Approach to Short-text Entity Linking