Node Attribute Completion in Knowledge Graphs with Multi-Relational Propagation

TL;DR

This paper introduces MrAP, a method for imputing missing numerical node attributes in knowledge graphs by propagating information through multi-relational structures using regression-based message passing.

Contribution

It presents a novel multi-relational propagation approach for node attribute completion, extending knowledge graph completion beyond link prediction.

Findings

Effective attribute imputation demonstrated on benchmark datasets

Outperforms baseline methods in accuracy

Iterative message passing improves prediction quality

Abstract

The existing literature on knowledge graph completion mostly focuses on the link prediction task. However, knowledge graphs have an additional incompleteness problem: their nodes possess numerical attributes, whose values are often missing. Our approach, denoted as MrAP, imputes the values of missing attributes by propagating information across the multi-relational structure of a knowledge graph. It employs regression functions for predicting one node attribute from another depending on the relationship between the nodes and the type of the attributes. The propagation mechanism operates iteratively in a message passing scheme that collects the predictions at every iteration and updates the value of the node attributes. Experiments over two benchmark datasets show the effectiveness of our approach.