Graph Neural Networks + LLM on Neo4j

Session Track: AI Engineering

Session Time: 10:00 pm - 10:30 pm November 6

Session description

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.

Speakers

Brian Shi

Senior Software Engineer, Neo4j

Brian has been working on graph algorithms, graph machine learning, and RAG on graphs with LLMs. His recent work includes building agents that reason over graphs by using graph algorithms as tools and leveraging methods from graph ML and algorithms to improve RAG on graphs.

Rishi Puri

PyG Engineering Lead, NVIDIA

Rishi Puri graduated from UC Berkeley and is a lead engineer for the Deep Learning FrameWork PyG at NVIDIA. He is also a core contributor to the open source PyG framework and community. His main focus is researching how to combine state of the art graph and language modeling techniques. He enjoys teaching about this work at Stanford, conferences, webinars, and through the PyG Slack and LinkedIn communities.