liveBook · Manning

Knowledge graph

As explained in Graph Neural Networks in Action

A knowledge graph is a heterogeneous graph that represents entities and relationships with explicit semantic context, metadata, and schema information.

A knowledge graph is a heterogeneous graph that represents entities and relationships with explicit semantic meaning. It adds relationship context, metadata, and schema information so systems can query patterns, analyze connections, and infer relationships. section 1.2.2

Model a knowledge graph by combining:

  • Typed entities such as Professors, Students, Papers, Topics, and Departments. section 1.2.2
  • Semantically meaningful relationships such as Supervises, Wrote, Authorship, and Inspires. section 1.2.2

University research network

Represent a physics department by connecting professors and students to papers, topics, and departments. Supervision, authorship, hierarchy, and inspiration remain distinct, enabling more specific queries than basic connectivity alone.

How Graph Neural Networks in Action covers it

How deep it goes
Defines semantic entities, relationships, metadata, and schemas, then illustrates them through an academic network without implementation details.
Examples
Uses a university physics research network containing professors, students, papers, topics, departments, and typed relationships.
What it assumes
Builds from heterogeneous graph terminology while contrasting semantic knowledge graphs with conventional connectivity-focused graphs.
What you can do after
Evaluate how explicit semantics and metadata enable more targeted graph queries and analysis.
How it connects
Connects heterogeneous graphs, metadata, schemas, semantic relationships, querying, and relationship inference.

Also explained in

Compare how 12 books explain knowledge graph →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Graph Neural Networks in Action. The section links point to the parts of the book it draws on.