liveBook · Manning

Graph data science

As explained in Knowledge Graphs and LLMs in Action

Graph data science is the application of graph algorithms and analytical methods to derive insights from connected data.

Graph data science applies graph algorithms and analytical methods to connected data. In a knowledge graph, an intellectual network can reveal influential people, popular subjects, and bridges between research communities. section 6.2

A practical analysis pipeline uses:

  • Select a meaningful subgraph, such as people connected through TALKED_ABOUT, TALKED_WITH, WORKS_WITH, and STUDENT_OF relationships. section 6.2
  • Calculate PageRank, Eigenvector centrality, node degree, and betweenness centrality to distinguish influencers, influencees, and community bridges. section 6.2

How Knowledge Graphs and LLMs in Action covers it

How deep it goes
Explains algorithm selection, visualization, and few-hop querying, but does not develop the algorithms mathematically.
Examples
Analyzes an intellectual network and traces influence around cyclotron research, funding, occupations, and universities.
What it assumes
Assumes a knowledge graph containing people, occupations, organizations, and typed relationships.
What you can do after
Apply it via Neo4j’s Graph Data Science library to identify influential nodes, bridges, and relevant multi-hop paths.
How it connects
Connects knowledge graphs, graph algorithms, centrality measures, network visualization, and Cypher queries.
Cover of Knowledge Graphs and LLMs in Action
liveBookmanning.com
Read Knowledge Graphs and LLMs in Action on liveBook Get the book at manning.com

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Knowledge Graphs and LLMs in Action. The section links point to the parts of the book it draws on.