Graph neural networks (GNN) is a tool that brings great predictive power to graph machine learning tasks such as link prediction and node classification. However, GNN architectures are typically very compute heavy and as such are not feasible to run at massive scale. In this talk, we will leverage the graph sampling features of the Neo4j Graph Data Science (GDS) library as well as the inductive power of GNNs to bring GNNs to scale. We will also show how the GDS Python Client can, with great performance, be used to integrate the GDS workflow with other GNN Python libraries.
Speakers: Adam Schill Collberg
Format: Full Session 30-45 min
Level: Advanced
Topics: #GraphDataScience, #Analytics, #MachineLearning, #Performance, #Python, #General, #Advanced
Region: AMERICAS
Slides: https://dist.neo4j.com/nodes-20202-slides/008%20GNNs%20at%20Scale%20With%20Graph%20Data%20Science%20Sampling%20and%20Python%20Client%20Integration%20-%20NODES2022%20AMERICAS%20Advanced%202%20-%20Adam%20Schill%20Collberg.pptx
Visit https://development.neo4j.dev/nodes-2022 learn more at https://development.neo4j.dev/developer/get-started and engage at https://community.neo4j.com