Keras Geometric is a library built on Keras (version 3+) designed for geometric deep learning, with a primary focus on Graph Neural Networks (GNNs). It provides modular building blocks to easily ...

On the algorithm level, GCoD integrates a split and conquer training strategy to polarize the graphs to be either denser or sparser in local neighborhoods without compromising the model accuracy, ...

Abstract: Graph Convolutional Networks (GCNs) are gaining attraction in AI research due to their ability to learn from graph data effectively. However, deploying GCNs on CPUs presents substantial ...

Abstract: Spatiotemporal prediction over graphs (STPG) is crucial for transportation systems. In existing STPG models, an adjacency matrix is an important component that captures the relations among ...