BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Learning with Knowledge Graphs
DTSTART:20181220T103000
DTEND:20181220T120000
DTSTAMP:20260407T183743Z
UID:1b167b386012d939e76af895161f3fd514138ff47f14e6a3f3757451
CATEGORIES:Conferences - Seminars
DESCRIPTION:Alberto García-Durán\nKnowledge Graphs (KGs) provide ways to
  organize\, manage and retrieve structure information\, playing an importa
 nt role in a number of AI applications\, such as recommender systems\, que
 stion answering or natural language generation. However\, a problem that i
 s common to all KGs is their incompleteness. In this talk we briefly discu
 ss different techniques to do knowledge graph completion\, with a special 
 emphasis on link prediction methods. Link prediction aims to complete quer
 ies wherein the answer is always an element of a closed vocabulary. Then w
 e will learn how to perform link prediction in temporal knowledge graphs\,
  wherein facts may be framed in time. This will be followed by an introduc
 tion to the numerical attribute prediction problem. Different to link pred
 iction\, the answer to the queries addressed in this problem is a numerica
 l value. Finally\, we will see that knowledge graphs and recommender syste
 ms share a number of similarities.\n\nAlberto García-Durán is a senior r
 esearcher at NEC Labs Europe\, Germany. He did his PhD at CNRS\, France. D
 uring his PhD he interned at MILA lab\, Canada. Prior to that\, he studied
  Sound&Image Engineering\, and Telecommunications Engineering in Spain. At
  a high level\, his research interests lie under the umbrella term Graph A
 I.\n 
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR