Thinking, Fast and Slow: Combining Vector Spaces and Knowledge Graphs

TL;DR

This paper introduces the VKG structure that unifies knowledge graphs and vector space models, enabling complex reasoning and search capabilities by combining their strengths, demonstrated through a cybersecurity application.

Contribution

The paper presents the VKG framework and a query engine that efficiently processes complex queries by decomposing them into subqueries optimized for each representation.

Findings

VKG can handle queries beyond the scope of individual models.

The system improves inference and search in cybersecurity data.

Experimental results validate VKG's effectiveness in real-world scenarios.

Abstract

Knowledge graphs and vector space models are robust knowledge representation techniques with individual strengths and weaknesses. Vector space models excel at determining similarity between concepts, but are severely constrained when evaluating complex dependency relations and other logic-based operations that are a strength of knowledge graphs. We describe the VKG structure that helps unify knowledge graphs and vector representation of entities, and enables powerful inference methods and search capabilities that combine their complementary strengths. We analogize this to thinking `fast' in vector space along with thinking 'slow' and `deeply' by reasoning over the knowledge graph. We have created a query processing engine that takes complex queries and decomposes them into subqueries optimized to run on the respective knowledge graph or vector view of a VKG. We show that the VKG structure can process specific queries that are not efficiently handled by vector spaces or knowledge graphs alone. We also demonstrate and evaluate the VKG structure and the query processing engine by developing a system called Cyber-All-Intel for knowledge extraction, representation and querying in an end-to-end pipeline grounded in the cybersecurity informatics domain.