Search Results for author: Ivan Girardi

Found 6 papers, 0 papers with code

Estimating the Adversarial Robustness of Attributions in Text with Transformers

no code implementations18 Dec 2022 Adam Ivankay, Mattia Rigotti, Ivan Girardi, Chiara Marchiori, Pascal Frossard

Finally, with experiments on several text classification architectures, we show that TEA consistently outperforms current state-of-the-art AR estimators, yielding perturbations that alter explanations to a greater extent while being more fluent and less perceptible.

Adversarial Robustness text-classification +2

Fooling Explanations in Text Classifiers

no code implementations ICLR 2022 Adam Ivankay, Ivan Girardi, Chiara Marchiori, Pascal Frossard

TEF can significantly decrease the correlation between unchanged and perturbed input attributions, which shows that all models and explanation methods are susceptible to TEF perturbations.

text-classification Text Classification

On the explainability of hospitalization prediction on a large COVID-19 patient dataset

no code implementations28 Oct 2021 Ivan Girardi, Panagiotis Vagenas, Dario Arcos-Díaz, Lydia Bessaï, Alexander Büsser, Ludovico Furlan, Raffaello Furlan, Mauro Gatti, Andrea Giovannini, Ellen Hoeven, Chiara Marchiori

We develop various AI models to predict hospitalization on a large (over 110$k$) cohort of COVID-19 positive-tested US patients, sourced from March 2020 to February 2021.

Feature Importance

Artificial Intelligence Decision Support for Medical Triage

no code implementations9 Nov 2020 Chiara Marchiori, Douglas Dykeman, Ivan Girardi, Adam Ivankay, Kevin Thandiackal, Mario Zusag, Andrea Giovannini, Daniel Karpati, Henri Saenz

Applying state-of-the-art machine learning and natural language processing on approximately one million of teleconsultation records, we developed a triage system, now certified and in use at the largest European telemedicine provider.

FAR: A General Framework for Attributional Robustness

no code implementations14 Oct 2020 Adam Ivankay, Ivan Girardi, Chiara Marchiori, Pascal Frossard

Therefore, we define a novel generic framework for attributional robustness (FAR) as general problem formulation for training models with robust attributions.

Cannot find the paper you are looking for? You can Submit a new open access paper.