Français Anglais
Accueil Annuaire Plan du site
Accueil > Evenements > Séminaires
Séminaire d'équipe(s) LaHDAK
Meta-Learning for Few-Shot Link Prediction in Knowledge Graphs
Taha Halal

13 December 2021, 13h00
Salle/Bat : 455/PCRI-N
Contact :

Activités de recherche : Intégration de données et de connaissances

Résumé :
Knowledge Graphs are collections of factual triplets, where each triplet (h, r, t) represents a relation r between a head entity h and a tail entity t.
Knowledge Graphs are widely used in a variety of applications such as question-answering, information retrieval, recommender systems, and natural language processing. Since knowledge graphs are usually incomplete, a fundamental problem is predicting the missing links.
However, a large portion of Knowledge Graph relations are long-tail. In other words, they have very few instances. But intuitively, the fewer training triples that one relation has, the more Knowledge Graph completion techniques could be of use. Therefore, it is crucial for models to be able to complete relations with limited numbers of triples.

Our work focuses on predicting missing relations in Knowledge Graphs with very few examples, what is known as Few-Shot Link Prediction in Knowledge Graphs. For that purpose we leverage Gradient-Based Meta-Learning methods which are efficient in fast adaptation of Neural Networks making them able to learn faster and better with very few samples.
In this talk, we will discuss the possibility of merging these widely used Meta-Learning methods with state-of-the-art Knowledge Graph embedding methods capable of capturing relation patterns such as symmetry, asymmetry, inversion, composition and transitivity. We believe being able to model these patterns is a bare minimum for having a good enough relation representation and a necessity for making good few-shot predictions.

Pour en savoir plus : https://www.lri.fr/membre.php?mb=2848
Séminaires
On the Interplay between Software Product Lines an
Raisonnement automatique
Tuesday 18 October 2022 - 14h15
Salle : 2013 - DIG-Moulon
Vander Alves .............................................

Combining randomized and observational data: Towar
Raisonnement automatique
Thursday 13 October 2022 - 10h30
Salle : 2011 - DIG-Moulon
Bénédicte Colnet .............................................

New Achievements of Artificial Intelligence in Mul
Raisonnement automatique
Tuesday 11 October 2022 - 14h15
Salle : 2013 - DIG-Moulon
.............................................

Definition and estimation of a variable importance
Raisonnement automatique
Thursday 22 September 2022 - 10h30
Salle : 2011 - DIG-Moulon
.............................................

Definition and estimation of a variable importance
Raisonnement automatique
Thursday 01 September 2022 - 10h30
Salle : 2011 - DIG-Moulon
Antoine Chambaz .............................................