FEDERICO SICILIANO

Dottore di ricerca

ciclo: XXXVI



Titolo della tesi: Architectural Components of Trustworthy Artificial Intelligence

Trustworthy Artificial Intelligence (AI) is a cornerstone of the digital era, encompassing the need for AI systems to be not only powerful but also transparent, resilient, and accountable. This thesis, titled Architectural Components of Trustworthy Artificial Intelligence, aims to explore the essential elements that underpin the development of AI systems that are inherently trustworthy. This work unfolds the foundations, methodologies, and innovations crucial for fostering trust in AI systems. The following summary provides an overview of the key contributions and insights of this thesis. The introduction provides a backdrop to the research, elucidating the motivations and objectives driving the study. It outlines the structure of the thesis, setting the stage for a systematic exploration. Starting our exploration, we delve into the fundamentals of Explainability-by-design. We introduce innovative concepts, including a novel generalization of artificial neurons, that redefine the foundations of model transparency. Furthermore, we investigate concept-based explainability, shedding light on how these networks provide insight into the decision-making processes of AI models. Turning our attention to the critical aspect of training trustworthy AI, we explore the development of loss functions tailored to address the challenges posed by noisy labels and missing data, particularly in recommender systems. We also show how integrating item relevance into the loss functions makes the model more resilient and dependable in the face of adversities. We then broaden our investigation introducing the concept of Trustworthy Auxiliary Frameworks: it extends beyond model-centric trustworthiness by incorporating elements such as counterfactual personalized recourse, active learning for misinformation detection, and retrieval augmentation. These auxiliary components address crucial aspects like data governance, monitoring, and interpretability, strengthening the AI system's trustworthiness throughout its lifecycle. The final part of this thesis summarizes key findings and contributions to the field of Trustworthy AI. It shows how we achieved the objectives outlined in the introduction, advancing the understanding and practical implementation of architectural components that enhance trustworthiness in AI systems across diverse domains. It also offers insights into future research directions, emphasizing the need for ongoing innovation and development in this critical domain. In conclusion, this thesis represents a significant step in the ongoing pursuit of Trustworthy AI. It stands as a valuable resource for researchers and practitioners striving to create AI systems that inspire trust and confidence. With the principles of trust, accountability, and transparency at its core, this research contributes to the collective effort of ensuring that AI serves humanity with the highest standards of ethics and responsibility.

Produzione scientifica

11573/1706240 - 2024 - Investigating the Robustness of Sequential Recommender Systems Against Training Data Perturbations
Betello, Filippo; Siciliano, Federico; Mishra, Pushkar; Silvestri, Fabrizio - 04b Atto di convegno in volume
congresso: European Conference on Information Retrieval, ECIR24 (Glasgow)
libro: ECIR 2024: Advances in Information Retrieval - (9783031560590; 9783031560606)

11573/1701860 - 2023 - RRAML: Reinforced Retrieval Augmented Machine Learning
Bacciu, A.; Cuconasu, F.; Siciliano, F.; Silvestri, F.; Tonellotto, N.; Trappolini, G. - 04b Atto di convegno in volume
congresso: 22nd International Conference of the Italian Association for Artificial Intelligence (AIxIA 2023 DP) co-located with 22nd International Conference of the Italian Association for Artificial Intelligence (AIxIA 2023) (Rome; Italy)
libro: Proceedings of the Discussion Papers - 22nd International Conference of the Italian Association for Artificial Intelligence (AIxIA 2023 DP) co-located with 22nd International Conference of the Italian Association for Artificial Intelligence (AIxIA 2023) - ()

11573/1689394 - 2023 - Integrating Item Relevance in Training Loss for Sequential Recommender Systems
Bacciu, Andrea; Siciliano, Federico; Tonellotto, Nicola; Silvestri, Fabrizio - 04b Atto di convegno in volume
congresso: RecSys '23: 17th ACM Conference on Recommender Systems (Singapore)
libro: RecSys '23: Proceedings of the 17th ACM Conference on Recommender Systems - (9798400702419)

11573/1673523 - 2023 - Deep active learning for misinformation detection using geometric deep learning
Barnabò, Giorgio; Siciliano, Federico; Castillo, Carlos; Leonardi, Stefano; Nakov, Preslav; Da San Martino, Giovanni; Silvestri, Fabrizio - 01a Articolo in rivista
rivista: ONLINE SOCIAL NETWORKS AND MEDIA (Elsevier) pp. - - issn: 2468-6964 - wos: (0) - scopus: 2-s2.0-85149058902 (4)

11573/1685080 - 2023 - Leveraging Inter-Rater Agreement for Classification in the Presence of Noisy Labels
Bucarelli, Maria Sofia; Cassano, Lucas; Siciliano, Federico; Mantrach, Amin; Silvestri, Fabrizio - 04b Atto di convegno in volume
congresso: IEEE Conference on Computer Vision and Pattern Recognition (Vancouver; Canada)
libro: IEEE Conference on Computer Vision and Pattern Recognition - (979-8-3503-0129-8)

11573/1700473 - 2023 - Concept Distillation in Graph Neural Networks
Charlotte Magister, Lucie; Barbiero, Pietro; Kazhdan, Dmitry; Siciliano, Federico; Ciravegna, Gabriele; Silvestri, Fabrizio; Jamnik, Mateja; Liò, Pietro - 04b Atto di convegno in volume
congresso: xAI 2023: 1st World Conference On eXplainable Artificial Intelligence (Lisbon, Portugal)
libro: World Conference on Explainable Artificial Intelligence - ()

11573/1684331 - 2023 - A Data-Driven Approach to Refine Predictions of Differentiated Thyroid Cancer Outcomes: A Prospective Multicenter Study
Grani, Giorgio; Gentili, Michele; Siciliano, Federico; Albano, Domenico; Zilioli, Valentina; Morelli, Silvia; Puxeddu, Efisio; Zatelli, Maria Chiara; Gagliardi, Irene; Piovesan, Alessandro; Nervo, Alice; Crocetti, Umberto; Massa, Michela; Teresa Samà, Maria; Mele, Chiara; Deandrea, Maurilio; Fugazzola, Laura; Puligheddu, Barbara; Antonelli, Alessandro; Rossetto, Ruth; D’Amore, Annamaria; Ceresini, Graziano; Castello, Roberto; Solaroli, Erica; Centanni, Marco; Monti, Salvatore; Magri, Flavia; Bruno, Rocco; Sparano, Clotilde; Pezzullo, Luciano; Crescenzi, Anna; Mian, Caterina; Tumino, Dario; Repaci, Andrea; Grazia Castagna, Maria; Triggiani, Vincenzo; Porcelli, Tommaso; Meringolo, Domenico; Locati, Laura; Spiazzi, Giovanna; Di Dalmazi, Giulia; Anagnostopoulos, Aris; Leonardi, Stefano; Filetti, Sebastiano; Durante, Cosimo - 01a Articolo in rivista
rivista: THE JOURNAL OF CLINICAL ENDOCRINOLOGY AND METABOLISM (-Springfield, Ill. : Charles C. Thomas -Philadelphia : J.B. Lippincott Co. -Baltimore, Md. : Issued for the Endocrine Society by the Williams & Wilkins Co. -Bethesda, MD : Endocrine Society -Chevy Chase, MD : Endocrine Society) pp. 1921-1928 - issn: 0021-972X - wos: WOS:000945280600001 (5) - scopus: 2-s2.0-85164846026 (4)

11573/1669807 - 2023 - The CAESAR Project for the ASI Space Weather Infrastructure
Laurenza, Monica; Del Moro, Dario; Alberti, Tommaso; Battiston, Roberto; Benella, Simone; Benvenuto, F.; Berrilli, Francesco; Bertello, I.; Bertucci, Bruna; Biasiotti, L.; Campi, Cristina; Carbone, Vincenzo; Casolino, M.; Cecchi Pestellini, C.; Chiappetta, Federica; Coco, I.; Colombo, S.; Consolini, Giuseppe; D'amicis, Raffaella; De Gasperis, Giancarlo; De Marco, R.; Del Corpo, Alfredo; Diego, Piero; Di Felice, Valeria; Di Fino, L.; Di Geronimo, C.; Faldi, F.; Ferrente, Fabiana; Feruglio, C.; Fiandrini, E.; Fiore, Fabrizio; Foldes, Raffaello; Formato, Valerio; Francisco, G.; Giannattasio, Fabio; Giardino, Marco; Giobbi, P.; Giovannelli, Luca; Giusti, M.; Gorgi, A.; Heilig, Balázs; Iafrate, Giulia; Ivanovski, S. L.; Jerse, G.; Korsos, M. B.; Lepreti, Fabio; Locci, D.; Magnafico, Carmelo; Mangano, V.; Marcucci, M. F.; Martucci, M.; Massetti, Stefano; Micela, G.; Milillo, Anna; Miteva, Rositsa; Molinaro, M.; Mugatwala, R.; Mura, A.; Napoletano, G.; Narici, L.; Neubüser, ; Nisticò, G.; Pauluzzi, M.; Perfetti, Alessandro; Perri, S.; Petralia, Antonino; Pezzopane, Michael; Piersanti, Mirko; Pietropaolo, Ermanno; Pignalberi, Alessio; Plainaki, C.; Polenta, G.; Primavera, Leonardo; Romoli, Giulia; Rossi, M.; Santarelli, Lucia; Santi Amantini, G.; Siciliano, Federico; Sindoni, Giuseppe; Spadoni, S.; Sparvoli, Roberta; Stumpo, M.; Tomassetti, Nicola; Tozzi, Roberta; Vagelli, Valerio; Vasantharaju, N; Vecchio, Antonio; Vellante, M.; Vernetto, S.; Francesco Vigorito, Carlo; West, Matthew; Zimbardo, Gaetano; Zucca, P.; Zuccarello, Francesca; Zuccon, Paolo - 01a Articolo in rivista
rivista: REMOTE SENSING (Basel : Molecular Diversity Preservation International) pp. 346- - issn: 2072-4292 - wos: WOS:000940422800001 (0) - scopus: 2-s2.0-85146851156 (0)

11573/1669826 - 2022 - FbMultiLingMisinfo: Challenging Large-Scale Multilingual Benchmark for Misinformation Detection
Barnabò, Giorgio; Siciliano, Federico; Castillo, Carlos; Leonardi, Stefano; Nakov, Preslav; Da San Martino, Giovanni; Silvestri, Fabrizio - 04b Atto di convegno in volume
congresso: International Joint Conference on Neural Networks (Padova; Italia)
libro: Proceedings 2022 International Joint Conference on Neural Networks (IJCNN) - (978-1-7281-8671-9; 978-1-6654-9526-4)

11573/1702415 - 2022 - Leveraging Deep Learning models to assess the temporal validity of Emotional Text Mining procedures
Greco, Francesca; Polli, Alessandro; Siciliano, Federico - 04b Atto di convegno in volume
congresso: 16th International Conference on Statistical Analysis of Textual Data (Napoli)
libro: JADT 2022 Proceedings: 16th International Conference on Statistical Analysis of Textual Data - (979-12-80153-30-2)

11573/1657031 - 2022 - NEWRON: A New Generalization of the Artificial Neuron to Enhance the Interpretability of Neural Networks
Siciliano, Federico; Bucarelli, Maria Sofia; Tolomei, Gabriele; Silvestri, Fabrizio - 04b Atto di convegno in volume
congresso: IEEE International Joint Conference on Neural Networks (Padova; Italia)
libro: IEEE International Joint Conference on Neural Networks - (978-1-7281-8671-9)

11573/1656589 - 2022 - Comparing long short-term memory and convolutional neural networks in {SYM}-H index forecasting
Siciliano, Federico; Consolini, Giuseppe; Giannattasio, Fabio - 04d Abstract in atti di convegno
congresso: EGU General Assembly 2022 (Vienna)
libro: EGU22 - ()

11573/1495477 - 2021 - Forecasting SYM-H Index: A Comparison Between LongShort-Term Memory and Convolutional Neural Networks
Siciliano, F.; Consolini, G.; Tozzi, R.; Gentili, M.; Giannattasio, F.; De Michelis, P. - 01a Articolo in rivista
rivista: SPACE WEATHER (Washington, D.C. : American Geophysical Union, [2003-) pp. - - issn: 1542-7390 - wos: WOS:000691671400007 (28) - scopus: 2-s2.0-85108635108 (28)

11573/1684888 - 2016 - Reconstruction of F-Region Electric Current Densities from more than 2 Years of Swarm Satellite Magnetic data
Tozzi, Roberta; Pezzopane, Michael; De Michelis, Paola; Pignalberi, Alessio; Siciliano, Federico - 04d Abstract in atti di convegno
congresso: AGU Fall Meeting 2016 (San Francisco)
libro: AGU Fall Meeting Abstracts - ()

© Università degli Studi di Roma "La Sapienza" - Piazzale Aldo Moro 5, 00185 Roma