Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Explore GraphNeuralNetworks.jl, an open-source Julia framework designed for deep learning on graphs, in this 28-minute conference talk from JuliaCon Global 2025. Discover how this flexible and high-performance library supports multiple GPU backends while working seamlessly with both sparse and dense graph representations. Learn to manipulate standard, heterogeneous, and temporal graphs with full support for attributes at node, edge, and graph levels. Master the framework's gather/scatter message-passing primitives for defining custom graph convolutional layers and explore its suite of popular layers for rapid experimentation. Gain insights into real-world applications and understand the ongoing developments within the GraphNeuralNetworks.jl ecosystem, presented by Aurora Rossi who demonstrates the library's capabilities for implementing sophisticated graph neural network architectures in Julia.
