no code implementations • 18 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.
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.
no code implementations • 28 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.
no code implementations • 9 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.
no code implementations • 14 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.
no code implementations • WS 2018 • Ivan Girardi, Pengfei Ji, An-phi Nguyen, Nora Hollenstein, Adam Ivankay, Lorenz Kuhn, Chiara Marchiori, Ce Zhang
In addition, a method to detect warning symptoms is implemented to render the classification task transparent from a medical perspective.