Enhancing Logical Expressiveness in Graph Neural Networks via Path-Neighbor Aggregation

TL;DR

This paper introduces PN-GNN, a novel graph neural network that enhances logical expressiveness by aggregating node-neighbor embeddings along reasoning paths, outperforming existing methods in modeling logical rules for knowledge graph reasoning.

Contribution

The paper proposes PN-GNN, a new GNN model that significantly improves logical expressive power by path-neighbor aggregation, with theoretical proof and empirical validation.

Findings

PN-GNN has strictly stronger expressive power than C-GNN.

PN-GNN's $(k+1)$-hop expressiveness exceeds that of $k$-hop.

PN-GNN achieves competitive performance on KG reasoning tasks.

Abstract

Graph neural networks (GNNs) can effectively model structural information of graphs, making them widely used in knowledge graph (KG) reasoning. However, existing studies on the expressive power of GNNs mainly focuses on simple single-relation graphs, and there is still insufficient discussion on the power of GNN to express logical rules in KGs. How to enhance the logical expressive power of GNNs is still a key issue. Motivated by this, we propose Path-Neighbor enhanced GNN (PN-GNN), a method to enhance the logical expressive power of GNN by aggregating node-neighbor embeddings on the reasoning path. First, we analyze the logical expressive power of existing GNN-based methods and point out the shortcomings of the expressive power of these methods. Then, we theoretically investigate the logical expressive power of PN-GNN, showing that it not only has strictly stronger expressive power than C-GNN but also that its $(k+1)$-hop logical expressiveness is strictly superior to that of $k$-hop. Finally, we evaluate the logical expressive power of PN-GNN on six synthetic datasets and two real-world datasets. Both theoretical analysis and extensive experiments confirm that PN-GNN enhances the expressive power of logical rules without compromising generalization, as evidenced by its competitive performance in KG reasoning tasks.