What can knowledge graph alignment gain with Neuro-Symbolic learning approaches?

TL;DR

This paper reviews current knowledge graph alignment methods and explores how neuro-symbolic learning approaches can enhance alignment quality, explainability, and reasoning capabilities.

Contribution

It provides an overview of the state of the art in KG alignment and discusses potential benefits and future research directions for integrating neuro-symbolic methods.

Findings

Neuro-symbolic approaches can improve explainability in KG alignment.

Hybrid models have potential to enhance reasoning and validation.

Current methods lack integration of logical reasoning with data-driven learning.

Abstract

Knowledge Graphs (KG) are the backbone of many data-intensive applications since they can represent data coupled with its meaning and context. Aligning KGs across different domains and providers is necessary to afford a fuller and integrated representation. A severe limitation of current KG alignment (KGA) algorithms is that they fail to articulate logical thinking and reasoning with lexical, structural, and semantic data learning. Deep learning models are increasingly popular for KGA inspired by their good performance in other tasks, but they suffer from limitations in explainability, reasoning, and data efficiency. Hybrid neurosymbolic learning models hold the promise of integrating logical and data perspectives to produce high-quality alignments that are explainable and support validation through human-centric approaches. This paper examines the current state of the art in KGA and explores the potential for neurosymbolic integration, highlighting promising research directions for combining these fields.