What can knowledge graph alignment gain with Neuro-Symbolic learning approaches?
This addresses the problem of integrating knowledge graphs across domains for data-intensive applications, but it is incremental as it reviews and suggests directions rather than presenting new results.
The paper examines knowledge graph alignment (KGA) algorithms, which currently lack logical reasoning and explainability, and explores how neuro-symbolic learning approaches could integrate logical and data perspectives to improve alignment quality and support human validation.
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.