Neural-Symbolic Message Passing with Dynamic Pruning

TL;DR

This paper introduces NSMP, a neural-symbolic framework for complex query answering on incomplete knowledge graphs, which generalizes to various query types, offers interpretability, and significantly improves inference speed over existing methods.

Contribution

The paper presents a novel neural-symbolic message passing framework with dynamic pruning that generalizes to arbitrary first-order logic queries without training and enhances inference efficiency.

Findings

NSMP achieves strong performance on benchmark datasets.

NSMP provides interpretable answers using symbolic reasoning.

NSMP speeds up inference by 2x to over 150x compared to previous methods.

Abstract

Complex Query Answering (CQA) over incomplete Knowledge Graphs (KGs) is a challenging task. Recently, a line of message-passing-based research has been proposed to solve CQA. However, they perform unsatisfactorily on negative queries and fail to address the noisy messages between variable nodes in the query graph. Moreover, they offer little interpretability and require complex query data and resource-intensive training. In this paper, we propose a Neural-Symbolic Message Passing (NSMP) framework based on pre-trained neural link predictors. By introducing symbolic reasoning and fuzzy logic, NSMP can generalize to arbitrary existential first order logic queries without requiring training while providing interpretable answers. Furthermore, we introduce a dynamic pruning strategy to filter out noisy messages between variable nodes. Experimental results show that NSMP achieves a strong performance. Additionally, through complexity analysis and empirical verification, we demonstrate the superiority of NSMP in inference time over the current state-of-the-art neural-symbolic method. Compared to this approach, NSMP demonstrates faster inference times across all query types on benchmark datasets, with speedup ranging from 2$\times$ to over 150$\times$.