G
Gabriele Ciravegna
Researcher at University of Florence
Publications - 29
Citations - 129
Gabriele Ciravegna is an academic researcher from University of Florence. The author has contributed to research in topics: Computer science & Artificial neural network. The author has an hindex of 6, co-authored 22 publications receiving 72 citations. Previous affiliations of Gabriele Ciravegna include University of Siena & Polytechnic University of Turin.
Papers
More filters
Journal ArticleDOI
The GH-EXIN neural network for hierarchical clustering
TL;DR: An important and very promising application of GH-EXIN in two-way hierarchical clustering, for the analysis of gene expression data in the study of the colorectal cancer is described.
Proceedings ArticleDOI
Human-Driven FOL Explanations of Deep Learning
TL;DR: This paper focuses on the case of multilabel classification, proposing a neural network that learns the relationships among the predictors associated to each class, yielding First-Order Logic (FOL)-based descriptions and can integrate human-driven preferences that guide the learning to explain process.
Journal ArticleDOI
Concept Embedding Models
M. Zarlenga,Pietro Barbiero,Gabriele Ciravegna,Giuseppe Marra,Francesco Giannini,Michelangelo Diligenti,Zohreh Shams,Frédéric Precioso,Stefano Melacci,Adrian Weller,Pietro Liò,Mateja Jamnik +11 more
TL;DR: This work proposes Concept Embedding Models, a novel family of concept bottleneck models which goes beyond the current accuracy-vs-interpretability trade-off by learning interpretable high-dimensional concept representations.
Posted Content
Can Domain Knowledge Alleviate Adversarial Attacks in Multi-Label Classifiers?
Stefano Melacci,Gabriele Ciravegna,Angelo Sotgiu,Ambra Demontis,Battista Biggio,Marco Gori,Fabio Roli +6 more
TL;DR: This paper surprisingly unveils that domain-knowledge constraints can help detect adversarial examples effectively, especially if such constraints are not known to the attacker.
Journal ArticleDOI
Encoding Concepts in Graph Neural Networks
Lucie Charlotte Magister,Pietro Barbiero,Dmitry Kazhdan,F. Siciliano,Gabriele Ciravegna,Fabrizio Silvestri,Pietro Liò,Mateja Jamnik +7 more
TL;DR: The Concept Encoder Module is introduced, the first differentiable concept-discovery approach for graph networks that makes graph networks explainable by design by discovering graph concepts and then using these to solve the task.