Graph Data Science
summary
Claims an integration stack rather than a proprietary platform: kglab abstraction layer ties RDF/JSON‑LD and Parquet storage to pandas, NumPy, scikit‑learn, PyTorch, RAPIDS, NetworkX and Neo4j connectors, offers SPARQL→DataFrame, SHACL validation, Jupyter notebooks and Docker Compose. Demonstrations include a quarter‑million recipes dataset turned into a knowledge graph with graph algorithms and embeddings, a reinforcement‑learning leaderboard to surface novel patterns, a Novartis example of 20% novel discoveries, and an explicit goal of aiming for trillion‑node graphs by year end.
AI-written summary · about
chapters (7)
- 0:00Introduction
- 1:38Presentation Overview
- 2:39Brief Story
- 8:02Pedagogy
- 13:48Graph Theory
- 16:23kglab
- 23:11Questions
related talks
46mBuilding Knowledge Graphs
30mHow Graph Data Science Can Turbocharge Your Knowledge Graph
44mBuilding Knowledge Graphs- 44mBuilding Knowledge Graphs
21mFrom Data to Knowledge to Action - The Graph Intelligence Platform
49mModern Graph Databases
01h 41mGraph Intelligence: Enhance Reasoning and Retrieval Using Graph Analytics
41mGraphGen: Conducting Graph Analytics over Relational Databases