Write your first graph neural network, complete with automatic feature engineering, visualization, and deployment, in this lab using popular open source libraries: PyGraphistry[AI], NVIDIA RAPIDS (cuDF, cuGraph, cuML), and GPU neural network ecosystems (DGL, PyG, TF). Graph neural networks are in a watershed moment, going from a method for Ph.D. teams to a tool that regular operational data teams can quickly and reliably deploy. We'll focus on PyGraphistry[AI], which enables streamlined graph AI workflows over the emerging GPU graph AI ecosystem. In the spirit of PyGraphistry[AI], this session is tailored for operational data teams needing easy streamlined automatic graph AI capabilities. Examples will span problems like spotting fraud in user clickstreams, detecting hackers in identity data, and making pricing predictions in large supply chain data. We'll provide data from these use cases, the training environment, and a walk through usage.
Prerequisite(s):
Please disregard any reference to "Event Code" for access to training materials. "Event Codes" are only valid during the original live session. Explore more training options offered by the NVIDIA Deep Learning Institute (DLI). Choose from an extensive catalog of self-paced, online courses or instructor-led virtual workshops to help you develop key skills in AI, HPC, graphics & simulation, and more.