Node Attribute Completion in Knowledge Graphs with Multi-Relational Propagation
This addresses the incompleteness of node attributes in knowledge graphs, which is a domain-specific problem for knowledge representation and reasoning, but the approach appears incremental as it builds on existing propagation techniques.
The paper tackles the problem of missing numerical attributes in knowledge graphs by proposing MrAP, a method that propagates information across multi-relational structures using regression functions and iterative message passing. Experiments on two benchmark datasets demonstrate its effectiveness.
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.