Graph Transformers on Neo4j

Session Track: AI Engineering

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

Session description

Advanced message-passing GNNs and graph transformers are being developed in the field of graph machine learning. At the same time, there has been rapid development and adoption of graph databases for machine learning and in particular graphRAG use cases. There is, however, still few direct connections and coupling of the two technologies. In this talk, we will show recent additions in PyG, the leading open-source graph ML library. We will also show how graph transformers can be trained on Neo4j data, leveraging the database and query engine natively. We will present future directions and opportunities for researchers and open-source contributors for PyG and Neo4j.

Speakers

Brian Shi

Senior Software Engineer, Neo4j

Brian has been working on graph algorithms, graph machine learning, and retrieval-and-reasoning on graphs with LLMs. His recent work includes finding ways of improving retrieval-augmented generation on graphs and building agents that reason over graphs by using graph algorithms as tools.

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.