Titolo: Deep Attributed Graph Embedding

Abstract: Real-world data are often characterized by an underlying relational structure, usually represented by graphs. Social and communication networks, citation networks, transport and utility networks are only some of the most common examples where we can observe complex relational interactions among a potentially large number of entities.
Graph Representation Learning (GRL) aims to learn a rich and low-dimensional node embedding while preserving the graph properties. Recent works have shown that jointly exploiting both structure and attributes information helps in learning a richer node representation. In this talk, we will review state-of-the-art approaches for node embedding and propose novel Deep Attributed Graph Embedding models for learning node representations based on both the topological structure and node attributes. Computational experiments on node classification and node clustering tasks will be discussed.