Zobrazeno 1 - 10
of 20
pro vyhledávání: '"Romero, Mario Alfonso"'
Counterfactual Explanation (CE) techniques have garnered attention as a means to provide insights to the users engaging with AI systems. While extensively researched in domains such as medical imaging and autonomous vehicles, Graph Counterfactual Exp
Externí odkaz:
http://arxiv.org/abs/2312.11747
Publikováno v:
ACM Computing Surveys, Volume 56, Issue 7, Article No. 171, pp 1-37, 2024
Graph Neural Networks (GNNs) perform well in community detection and molecule classification. Counterfactual Explanations (CE) provide counter-examples to overcome the transparency limitations of black-box models. Due to the growing attention in grap
Externí odkaz:
http://arxiv.org/abs/2210.12089
Machine Learning (ML) systems are a building part of the modern tools which impact our daily life in several application domains. Due to their black-box nature, those systems are hardly adopted in application domains (e.g. health, finance) where unde
Externí odkaz:
http://arxiv.org/abs/2206.02957
Autor:
Prado-Romero, Mario Alfonso1 (AUTHOR) marioalfonso.prado@gssi.it, Prenkaj, Bardh2 (AUTHOR) prenkaj@di.uniroma1.it, Stilo, Giovanni3 (AUTHOR) giovanni.stilo@univaq.it, Giannotti, Fosca4 (AUTHOR) fosca.giannotti@sns.it
Publikováno v:
ACM Computing Surveys. Jul2024, Vol. 56 Issue 7, p1-37. 37p.
Autor:
Prado-Romero, Mario Alfonso1 (AUTHOR) mario.prado@matcom.uh.cu, Coto-Santiesteban, Alex2 (AUTHOR), Celi, Alessandro3 (AUTHOR), Stilo, Giovanni3 (AUTHOR)
Publikováno v:
Intelligent Data Analysis. 2020 Supplement 1, Vol. 24, p123-140. 18p.
Autor:
Prado-Romero, Mario Alfonso1 (AUTHOR) mario.prado@matcom.uh.cu, Coto-Santiesteban, Alex2 (AUTHOR), Celi, Alessandro3 (AUTHOR), Stilo, Giovanni3 (AUTHOR)
Publikováno v:
Intelligent Data Analysis. 2020 Supplement 1, Vol. 24, p123-140. 18p.
Publikováno v:
In Procedia - Social and Behavioral Sciences 2011 16:270-281
In recent years, Graph Neural Networks have reported outstanding performance in tasks like community detection, molecule classification and link prediction. However, the black-box nature of these models prevents their application in domains like heal
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7e75bed8379e321f92e462a88a039cf4