1 code implementation • 3 May 2024 • Miruna Beţianu, Abele Mălan, Marco Aldinucci, Robert Birke, Lydia Chen
In this paper, we design DALLMi, Domain Adaptation Large Language Model interpolator, a first-of-its-kind semi-supervised domain adaptation method for text data models based on LLMs, specifically BERT.
no code implementations • 31 Mar 2023 • Bruno Casella, Roberto Esposito, Carlo Cavazzoni, Marco Aldinucci
Data carry a value that might vanish when shared with others; the ability to avoid sharing the data enables industrial applications where security and privacy are of paramount importance, making it possible to train global models by implementing only local policies which can be run independently and even on air-gapped data centres.
1 code implementation • 19 Mar 2023 • Bruno Casella, Roberto Esposito, Antonio Sciarappa, Carlo Cavazzoni, Marco Aldinucci
Training Deep Learning (DL) models require large, high-quality datasets, often assembled with data from different institutions.
1 code implementation • 8 Mar 2023 • Gianluca Mittone, Walter Riviera, Iacopo Colonnelli, Robert Birke, Marco Aldinucci
MAFL marries a model-agnostic FL algorithm, AdaBoost. F, with an open industry-grade FL framework: Intel OpenFL.
1 code implementation • 15 Feb 2023 • Gianluca Mittone, Nicolò Tonci, Robert Birke, Iacopo Colonnelli, Doriana Medić, Andrea Bartolini, Roberto Esposito, Emanuele Parisi, Francesco Beneventi, Mirko Polato, Massimo Torquati, Luca Benini, Marco Aldinucci
Federated Learning (FL) and Edge Inference are examples of DML.
1 code implementation • 15 Feb 2023 • Gianluca Mittone, Filip Svoboda, Marco Aldinucci, Nicholas D. Lane, Pietro Lio
Aggregating pharmaceutical data in the drug-target interaction (DTI) domain has the potential to deliver life-saving breakthroughs.
no code implementations • 14 Dec 2022 • Marco Aldinucci, Livio Bioglio, Cristina Calcagno, Mario Coppo, Ferruccio Damiani, Maurizio Drocco, Elena Grassi, Pablo Ramón, Eva Sciacca, Salvatore Spinella, Angelo Troina
The modelling and analysis of biological systems has deep roots in Mathematics, specifically in the field of Ordinary Differential Equations.
1 code implementation • 21 Jun 2022 • Federica Proietto Salanitri, Giovanni Bellitto, Simone Palazzo, Ismail Irmakci, Michael B. Wallace, Candice W. Bolan, Megan Engels, Sanne Hoogenboom, Marco Aldinucci, Ulas Bagci, Daniela Giordano, Concetto Spampinato
Early detection of precancerous cysts or neoplasms, i. e., Intraductal Papillary Mucosal Neoplasms (IPMN), in pancreas is a challenging and complex task, and it may lead to a more favourable outcome.
1 code implementation • 20 Jun 2022 • Matteo Pennisi, Federica Proietto Salanitri, Giovanni Bellitto, Bruno Casella, Marco Aldinucci, Simone Palazzo, Concetto Spampinato
In the medical field, multi-center collaborations are often sought to yield more generalizable findings by leveraging the heterogeneity of patient and clinical data.
no code implementations • 2 Aug 2021 • Iacopo Colonnelli, Barbara Cantalupo, Concetto Spampinato, Matteo Pennisi, Marco Aldinucci
This is the leitmotif of the convergence between HPC and AI.
no code implementations • 25 Jun 2018 • Paolo Viviani, Maurizio Drocco, Marco Aldinucci
This work aims to assess the state of the art of data parallel deep neural network training, trying to identify potential research tracks to be exploited for performance improvement.