Valda — Valeur à partir des données
Recherche
Séminaire
Membres
Publications
Séminaire Valda : Yann Ramusat
12 avril 2022, 10:30-11:30. ENS, S16 The Semiring-Based Provenance Framework for Graph Databases L’augmentation du volume de données collectées par des capteurs et générées par des interactions humaines a mené à l’utilisation des bases de données orientées graphes en tant que modèle de représentation efficace pour les données complexes. Les…
Séminaire Valda : Michaël Thomazo
8 avril 2022, 10:30-11:30. ENS, S16 Capturing Homomorphism-Closed Decidable Queries with Existential Rules Existential rules are a well studied ontology-mediated query language for which the chase represents a generic computational approach for query answering. It is straightforward that existential rule queries exhibiting chase termination are decidable and can only recognize…
Séminaire Valda : Debabrota Basu
Debabrota Basu, Inria Lille. 11 mars 2022, 10:30-11:30. ENS S16. Verifying and Explaining Unfairness of Machine Learning Algorithms In recent years, machine learning (ML) algorithms have been deployed in safety-critical and high-stake decision-making, where the fairness or unbiasedness of algorithms bears significant importance. Fairness in ML centres on detecting bias…
Séminaire Valda : Mikaël Monet
Mikaël Monet, Inria Lille. 25 février 2022, 10:30-11:30. ENS, S16. Shapley Values for Relational Databases and Machine Learning The Shapley value is a game-theoretic function that can be used to distribute the wealth of a team in a cooperative game. This function has strong theoretical justifications has been applied across…
