Efficient and Scalable Neural Symbolic Search for Knowledge Graph Complex Query Answering

TL;DR

This paper introduces a scalable neural symbolic search framework for complex knowledge graph query answering, significantly reducing computational costs while maintaining high accuracy, enabling handling larger graphs and more complex queries.

Contribution

It presents novel constraint strategies and an approximate local search algorithm to improve scalability and efficiency of neural symbolic CQA methods.

Findings

Reduces symbolic search computational load by 90%

Maintains nearly the same accuracy as previous methods

Effectively handles larger knowledge graphs and complex queries

Abstract

Complex Query Answering (CQA) aims to retrieve answer sets for complex logical formulas from incomplete knowledge graphs, which is a crucial yet challenging task in knowledge graph reasoning. While neuro-symbolic search utilized neural link predictions achieve superior accuracy, they encounter significant complexity bottlenecks: (i) Data complexity typically scales quadratically with the number of entities in the knowledge graph, and (ii) Query complexity becomes NP-hard for cyclic queries. Consequently, these approaches struggle to effectively scale to larger knowledge graphs and more complex queries. To address these challenges, we propose an efficient and scalable symbolic search framework. First, we propose two constraint strategies to compute neural logical indices to reduce the domain of variables, thereby decreasing the data complexity of symbolic search. Additionally, we introduce an approximate algorithm based on local search to tackle the NP query complexity of cyclic queries. Experiments on various CQA benchmarks demonstrate that our framework reduces the computational load of symbolic methods by 90\% while maintaining nearly the same performance, thus alleviating both efficiency and scalability issues.