Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Vargas Vieyra, Mariana"'
Autor:
Vargas Vieyra, Mariana
Publikováno v:
PODS 2022-Workshop on Principles of Distribution Shift
PODS 2022-Workshop on Principles of Distribution Shift, Jul 2022, Baltimore, United States. pp.1-8
PODS 2022-Workshop on Principles of Distribution Shift, Jul 2022, Baltimore, United States. pp.1-8
International audience; The problem of discovering a structure that fits a collection of vector data is of crucial importance for a variety of applications. Such problems can be framed as Laplacian constrained Gaussian Graphical Model inference. Exis
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od_______165::39813d7db13dac3990061cd2f6532c66
https://inria.hal.science/hal-03697993v2/document
https://inria.hal.science/hal-03697993v2/document
Autor:
Vargas Vieyra, Mariana
Publikováno v:
Artificial Intelligence [cs.AI]. Université de Lille, 2021. English. ⟨NNT : 2021LILUB013⟩
Computer Science [cs]. Inria Lille Nord Europe-Laboratoire CRIStAL-Université de Lille, 2021. English. ⟨NNT : ⟩
Computer Science [cs]. Inria Lille Nord Europe-Laboratoire CRIStAL-Université de Lille, 2021. English. ⟨NNT : ⟩
In the last few years Machine Learning methods have been incorporated in various Natural Language Processing systems.As a result, these methods have shown impressive results in a variety of tasks across multiple domains, in particular, through superv
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::76820660b85abbb14d1b5bd7e4d41c38
https://theses.hal.science/tel-03539532/file/These_VARGAS_VIEYRA_Mariana.pdf
https://theses.hal.science/tel-03539532/file/These_VARGAS_VIEYRA_Mariana.pdf
Publikováno v:
Graph Representation Learning workshop, NeurIPS
Graph Representation Learning workshop, NeurIPS, 2019, Vancouver, Canada
Graph Representation Learning workshop, NeurIPS, 2019, Vancouver, Canada
Workshop paper; International audience; In this paper we address the problem of graph-based semi-supervised learning in tasks where a graph describing the relationships between data points is not available. We propose a method to jointly learn the gr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::9c915f266b45ffd23aa0f94f0777e039
https://hal.archives-ouvertes.fr/hal-03501846/document
https://hal.archives-ouvertes.fr/hal-03501846/document