1285. sredin seminar: Felipe Vaca: An introduction to graph embeddings and urban networks

The most recent approaches for learning representations of graphs have been motivated for achieving higher efficiency on graph algorithms and overcoming feature engineering problems.  One of such approaches consists on graph embedding methods, which are representations in a vector space that try to preserve the graph properties. Despite these methods have been already used in other areas (e.g., Biology, Social Sciences, and Linguistics) for machine learning tasks (e.g, node classification, node clustering, link prediction, graph classification, and social network alignment), other application scenarios are yet to be explored. In this context, this talk will introduce some ideas about graph embeddings and propose an application of them for analyzing urban networks.