How Graph Data Science Can Turbocharge Your Knowledge Graph
summary
Defines a practical pipeline: load data into Neo4j, run 65+ algorithms (PageRank, centrality, community detection), produce node vectors with node2vec, GraphSAGE, FastRP, and run classification/link‑prediction/regression pipelines or export vectors to Python for custom models. Shows knowledge‑graph completion and a chatbot use case that achieves 90% retention at scale, cites JPMorgan papers, and recommends Neo4j Sandbox for a five‑minute sandboxed start.
AI-written summary · about
chapters (12)
- 0:00Introduction to talk
- 1:03Neo4j company overview
- 2:49What are knowledge graphs
- 8:06Growing knowledge graphs
- 12:20Graph data science explained
- 16:32Centrality algorithms demo
- 19:45Graph embeddings explained
- 23:39Graph neural networks power
- 25:41Knowledge graph completion demo
- 27:05Language models and graphs
- 28:08Getting started with Neo4j
- 29:30Q&A and closing
related talks
30mGraph Data Science
01h 41mGraph Intelligence: Enhance Reasoning and Retrieval Using Graph Analytics
28mRole of Knowledge Graphs in Mental Health Diagnosis and Cure
40mKnowledge graphs --enter- the Hype Cycle
26mGraph Databases will change your (freakin') life
27mAdaptive Knowledge Graphs for Dynamic RAG Systems
22mThe Nexus of Innovation: How Knowledge Graphs Fuel AI Scientific Breakthroughs
49mModern Graph Databases