Knowledge Enhanced Graph Neural Networks for Graph Completion

TL;DR

This paper introduces KeGNN, a neuro-symbolic framework that enhances graph neural networks with prior knowledge to improve graph completion tasks like node classification and link prediction.

Contribution

The paper presents KeGNN, a novel framework combining neural and symbolic methods to incorporate prior knowledge into GNNs for better graph completion performance.

Findings

KeGNN improves accuracy on benchmark datasets.

Knowledge integration enhances GNN robustness.

KeGNN outperforms baseline models in node classification.

Abstract

Graph data is omnipresent and has a wide variety of applications, such as in natural science, social networks, or the semantic web. However, while being rich in information, graphs are often noisy and incomplete. As a result, graph completion tasks, such as node classification or link prediction, have gained attention. On one hand, neural methods, such as graph neural networks, have proven to be robust tools for learning rich representations of noisy graphs. On the other hand, symbolic methods enable exact reasoning on graphs.We propose Knowledge Enhanced Graph Neural Networks (KeGNN), a neuro-symbolic framework for graph completion that combines both paradigms as it allows for the integration of prior knowledge into a graph neural network model.Essentially, KeGNN consists of a graph neural network as a base upon which knowledge enhancement layers are stacked with the goal of refining predictions with respect to prior knowledge.We instantiate KeGNN in conjunction with two state-of-the-art graph neural networks, Graph Convolutional Networks and Graph Attention Networks, and evaluate KeGNN on multiple benchmark datasets for node classification.