The Fifth Graph Normal Form (5GNF): A Trait-Based Framework for Metadata Normalization in Property Graphs

TL;DR

The paper proposes 5GNF, a trait-based normalization framework for property graphs that reduces redundancy, enhances semantic clarity, and improves maintainability by externalizing recurring metadata as shared traits.

Contribution

It introduces the 5GNF normalization framework, formalizes trait functional dependencies, and provides an algorithm for extracting reusable traits in property graphs.

Findings

Reduces redundant metadata in property graphs.

Maintains competitive query performance after normalization.

Improves semantic clarity and reusability of graph schemas.

Abstract

Graph databases are widely used in systems that manage rich metadata, yet current modelling practices often embed descriptive attributes directly in nodes, leading to redundancy and inconsistent semantics. This paper introduces the Fifth Graph Normal Form (5GNF), a trait-based normalization framework for property graphs that represents recurring metadata as canonical Trait Nodes connected through HAS_TRAIT relationships. We formalize trait functional dependencies (tFDs) and present the TraitExtraction5GNF algorithm for identifying and extracting reusable traits. The approach is implemented in Neo4j and evaluated using the widely used Northwind dataset, which contains substantial duplication in location and shipping metadata. The normalization process externalizes recurring metadata into shared traits, removes thousands of redundant attribute instances, reduces schema complexity, and simplifies analytical queries. Experimental results indicate that the normalized model maintains competitive performance while improving semantic clarity and reusability of metadata structures. These findings suggest that 5GNF provides a practical normalization framework for property graph schemas and contributes toward more consistent and maintainable graph data models.