Live from NODES 2025 | Graph Neural Networks + LLM on Neo4j

Graph Neural Networks + LLM on Neo4j
Advanced message-passing graph neural networks (GNNs) and graph transformers are rapidly evolving in the field of graph machine learning. At the same time, graph databases are seeing increased adoption for machine learning and, in particular, for retrieval-augmented generation (GraphRAG) use cases.

In this talk, we will showcase recent additions to PyTorch Geometric (PyG), the leading open-source graph ML library, featuring enhanced integrations with Neo4j and LLMs. We will also demonstrate how GNN+LLM can be trained on Neo4j data to improve GraphRAG. Finally, we will discuss future directions and opportunities for researchers and open-source contributors in both PyG and Neo4j to further strengthen the integration between GNNs, LLMs, and Neo4j using PyG.

Resources:
Get Started with Aura – https://bit.ly/3LOLrjh
Deployment Center – https://bit.ly/4jOelM3
Ground AI Systems and Agents with Neo4j – https://bit.ly/4oVsnyb

Speakers: Brian Shi, Rishi Puri
View Presentation: https://drive.google.com/file/d/1vyY2t99zsRjSMcCQIJjL2nZ3bE_PUIfA/view?usp=drive_link

#nodes2025 #neo4j #graphdatabase #graphrag #knowledgegraph