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

2025-05-13

AI Summary

Complex Query Answering (CQA) over knowledge graphs faces dual scalability challenges: quadratic growth in data complexity with entity scale, and NP-hard query complexity induced by cyclic patterns. This work proposes a neuro-symbolic collaborative framework to address these limitations. Its core contributions are: (1) a neural-logic indexing mechanism coupled with constraint propagation, which drastically prunes the variable search space; and (2) a local-search-based approximate symbolic reasoning algorithm—the first to enable efficient, scalable processing of cyclic queries. Evaluated on multiple CQA benchmarks, the method reduces computational load by 90% while preserving near-lossless accuracy. It thus significantly enhances real-time logical reasoning capability for complex queries over large-scale knowledge graphs.

Technology Category

• Knowledge Representation and Reasoning: Computational Complexity of Reasoning
• Machine Learning: Neuro-Symbolic Learning
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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.

Problem

• Reducing data complexity in knowledge graph query answering
• Addressing NP-hard query complexity for cyclic queries
• Improving scalability of neuro-symbolic search frameworks

Innovation

• Uses neural logical indices to reduce variable domains
• Implements local search for NP-hard cyclic queries
• Reduces computational load by 90% with similar performance