We investigate fundamental techniques in Graph Deep Learning, a new framework that combines graph theory and deep neural networks to tackle complex data domains in physical science, natural language processing, computer vision, and combinatorial optimization.
Identify universal building blocks for robust and scalable GNNs.
Representation learning for drawings via graphs with geometric and temporal information.
Scalable deep learning systems for practical NP-Hard combinatorial problems such as the TSP.
Chemical synthesis, structure and property prediction using deep neural networks.
Graph Neural Network architectures for inductive representation learning on arbitrary graphs.