A Quick Tour of Graph Representation Learning

Abstract

Statistical learning on large-scale knowledge graphs has proven to be effective for a number of machine learning tasks, notably link prediction. I will give an overview of the latest developments, focusing on knowledge graph embedding models which are neural architectures designed to predict links in large-scale knowledge graphs. I will also present AmpliGraph, an opensource library we developed here at Accenture Labs Dublin, and I will talk you through how we use it in our team. http://ampligraph.org/

Keywords: machine learning, knowledge graphs, knowledge graph embeddings, graph representation learning

Short Bio

Luca Costabello is research scientist in Accenture Labs Dublin. His research interests span knowledge graphs applications, machine learning for graphs, and explainable AI. Before joining Accenture, Luca was research scientist in Fujitsu Ireland, where he focused on knowledge discovery from graph-based knowledge bases in various industry scenarios. He obtained a PhD in computer science from the University of Nice Sophia Antipolis (France), during a stint at the French Institute for Research in Computer Science (Inria), where he focused on context-aware consumption of Linked Data. Luca worked as research engineer at Telecom Italia in Turin (Italy), mostly on data mining for location-based services. He received an MSc and a BSc in computer engineering from the Polytechnic University in Turin. More on https://luca.costabello.info

Venue