Graph Machine Learning

Graph data are present in a myriad of modern computer sciences systems and applications. Examples include data generated over social, brain, financial, power, water and sensor networks. Because these data have a complicated structure they require different tools conventionally used in machine and deep learning to develop end to end solutions. These solutions falls generally under the umbrella of graph-based machine learning and can be used to perform recommendations, detect anomalies in the brain, predict financial crisis, estimate the sate of a power or water network, and coordinate group of autonomous moving sensor, to name a few.

This course deals with the foundations and principles of machine and deep learning for network data. Topics include: unsupervised and semi-supervised learning on graphs; graph representation learning; graph signal processing; graph convolutions; graph neural networks; spatiotemporal learning on graphs; scalable algorithms; explainability and privacy of graph neural networks.