ALESSIO RAGNO

Dottorando

ciclo: XXXVII
email: alessio.ragno@uniroma1.it
edificio: Department of Computer, Control, and Management Engineering, Via Ariosto, 25, 00185 Roma RM
stanza: B121




supervisore: Roberto Capobianco
co-supervisore: Daniele Nardi

Ricerca: Topology-based Explanations for Neural Networks

I am a Ph.D. student in Artificial Intelligence under the supervision of prof. Roberto Capobianco. I am interested in the application of AI to different scientific fields and I think that Explainable AI could play an essential role for this purpose. My Ph.D. project consists in developing model-specific XAI methods, using a topology-based approach, in order to identify and learn data representations able to provide human-interpretable explanations of the neural network predictions.I have an M.Sc. degree in AI & Robotics and a B.Sc. degree in Computer and Control Engineering. I have also some background in the application of AI to chemistry and drug discovery gained through abroad experience at the University of North Carolina and collaborations with the Pharmaceutical Chemistry and Technology Department at the Sapienza University of Rome.

Produzione scientifica

11573/1696769 - 2023 - Understanding Deep RL agent decisions: a novel interpretable approach with trainable prototypes
Borzillo, Caterina; Ragno, Alessio; Capobianco, Roberto - 04b Atto di convegno in volume
congresso: XAI.it 2023: Italian Workshop on Explainable Artificial Intelligence 2023 (Rome)
libro: CEUR Workshop Proceedings Vol-3518 - ()

11573/1690926 - 2023 - Memory Replay For Continual Learning With Spiking Neural Networks
Proietti, Michela; Ragno, Alessio; Capobianco, Roberto - 04b Atto di convegno in volume
congresso: 2023 IEEE 33rd International Workshop on Machine Learning for Signal Processing (MLSP) (Rome; Italy)
libro: 2023 IEEE 33rd International Workshop on Machine Learning for Signal Processing (MLSP) - (979-8-3503-2411-2)

11573/1691190 - 2023 - Explainable AI in drug discovery: self-interpretable graph neural network for molecular property prediction using concept whitening
Proietti, Michela; Ragno, Alessio; Rosa, Biagio La; Ragno, Rino; Capobianco, Roberto - 01a Articolo in rivista
rivista: MACHINE LEARNING (Kluwer Academic Publishers / Massachusetts:PO Box 358, Accord Station:Hingham, MA 02018:(617)871-6600) pp. - - issn: 0885-6125 - wos: WOS:001091343300001 (0) - scopus: 2-s2.0-85175337233 (0)

11573/1659035 - 2022 - Ligand-based and structure-based studies to develop predictive models for {SARS}-{CoV}-2 main protease inhibitors through the 3d-qsar.com portal
Proia, Eleonora; Ragno, Alessio; Antonini, Lorenzo; Sabatino, Manuela; Mladenović, Milan; Capobianco, Roberto; Ragno, Rino - 01a Articolo in rivista
rivista: JOURNAL OF COMPUTER-AIDED MOLECULAR DESIGN (-SPRINGER, VAN GODEWIJCKSTRAAT 30, DORDRECHT, NETHERLANDS, 3311 GZ -Kluwer Academic Publishers:Journals Department, PO Box 322, 3300 AH Dordrecht Netherlands:011 31 78 6576050, EMAIL: frontoffice@wkap.nl, kluweronline@wkap.nl, INTERNET: http://www.kluwerlaw.com, Fax: 011 31 78 6576254) pp. 483-505 - issn: 0920-654X - wos: WOS:000812582700001 (3) - scopus: 2-s2.0-85132189914 (3)

11573/1680634 - 2022 - Explainable AI in drug design: self-interpretable graph neural network for molecular property prediction using concept whitening
Proietti, Michela; Ragno, Alessio; Capobianco, Roberto - 04f Poster
congresso: 3rd Molecules Medicinal Chemistry Symposium: Shaping Medicinal Chemistry for the New Decade (Rome; Italy)
libro: 2022 - ()

11573/1681948 - 2022 - Py-Graph: An Easy-To-Use Interface for Building Graph-Based QSAR Models
Ragno, Alessio; Capobianco, Roberto; Ragno, Rino - 04f Poster
congresso: 23rd European Symposium on Quantitative Structure-Activity Relationship (Heidelberg, Germany)
libro: 2022 - ()

11573/1662081 - 2022 - Prototype-based Interpretable Graph Neural Networks
Ragno, Alessio; La Rosa, Biagio; Capobianco, Roberto - 01a Articolo in rivista
rivista: IEEE TRANSACTIONS ON ARTIFICIAL INTELLIGENCE (Piscataway NJ: IEEE) pp. 1-11 - issn: 2691-4581 - wos: (0) - scopus: 2-s2.0-85142856655 (2)

11573/1583175 - 2021 - Machine learning data augmentation as a tool to enhance quantitative composition–activity relationships of complex mixtures. A new application to dissect the role of main chemical components in bioactive essential oils
Ragno, A.; Baldisserotto, A.; Antonini, L.; Sabatino, M.; Sapienza, F.; Baldini, E.; Buzzi, R.; Vertuani, S.; Manfredini, S. - 01a Articolo in rivista
rivista: MOLECULES (Basel: MDPI Berlin: Springer, 1996-) pp. 1-12 - issn: 1420-3049 - wos: WOS:000714423500001 (3) - scopus: 2-s2.0-85117456880 (3)

11573/1635487 - 2021 - Semi-Supervised GCN for learning Molecular Structure-Activity Relationships
Ragno, Alessio; Savoia, Dylan; Capobianco, Roberto - 04f Poster
congresso: ELLIS Machine Learning for Molecules Workshop (Online)
libro: 2021 - ()

11573/1645783 - 2021 - Molecule Generation from Input-Attribution over Graph Convolutional Networks
Savoia, Dylan; Ragno, Alessio; Capobianco, Roberto - 04f Poster
congresso: ELLIS Machine Learning for Molecules Workshop (Online)
libro: 2021 - ()

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