Efficient Probabilistic Logic Reasoning with Graph Neural Networks

TL;DR

This paper introduces ExpressGNN, a novel graph neural network variant that combines the strengths of Markov Logic Networks and GNNs to enable efficient probabilistic logic reasoning at scale.

Contribution

The paper proposes ExpressGNN, a new GNN-based approach for variational inference in MLNs, improving efficiency and effectiveness in probabilistic logic reasoning.

Findings

ExpressGNN achieves competitive accuracy on benchmark datasets.

The method significantly reduces inference time compared to traditional MLN methods.

Experiments demonstrate the model's ability to handle large-scale knowledge graph reasoning tasks.

Abstract

Markov Logic Networks (MLNs), which elegantly combine logic rules and probabilistic graphical models, can be used to address many knowledge graph problems. However, inference in MLN is computationally intensive, making the industrial-scale application of MLN very difficult. In recent years, graph neural networks (GNNs) have emerged as efficient and effective tools for large-scale graph problems. Nevertheless, GNNs do not explicitly incorporate prior logic rules into the models, and may require many labeled examples for a target task. In this paper, we explore the combination of MLNs and GNNs, and use graph neural networks for variational inference in MLN. We propose a GNN variant, named ExpressGNN, which strikes a nice balance between the representation power and the simplicity of the model. Our extensive experiments on several benchmark datasets demonstrate that ExpressGNN leads to effective and efficient probabilistic logic reasoning.