Science and technology for the explanation of AI decision making

GLOR-FLEX: Local to Global Rule-Based EXplanations for Federated Learning

Auteurs: Rami Haffar, Francesca Naretto, David Sánchez, Anna Monreale, Josep Domingo-Ferrer
Publié dans: 2024 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), 2024, Page(s) 1-9
Éditeur: IEEE
DOI: 10.1109/fuzz-ieee60900.2024.10611878

Investigating Debiasing Effects on Classification and Explainability

Auteurs: Marchiori Manerba Marta, Morini Virginia
Publié dans: Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2022
Éditeur: Springer, Cham
DOI: 10.1007/978-3-031-23618-1_32

Explaining Siamese Networks in Few-Shot Learning for Audio Data

Auteurs: Fedele Andrea, Guidotti Riccardo, Pedreschi Dino
Publié dans: Discovery Science 25th International Conference, DS 2022, Proceedings, 2022
Éditeur: Springer, Cham
DOI: 10.1007/978-3-031-18840-4_36

TRIPLEx: Triple Extraction for Explanation

Auteurs: Mattia Setzu, Anna Monreale, Pasquale Minervini
Publié dans: IEEE Third International Conference on Cognitive Machine Intelligence (CogMI), 2021
Éditeur: IEEE
DOI: 10.1109/cogmi52975.2021.00015

Geolet: An Interpretable Model for Trajectory Classification

Auteurs: Landi Cristiano,Spinnato Francesco, Guidotti Riccardo, Monreale Anna, Nanni Mirco
Publié dans: Proceedings of the 2023 conference Advances in Intelligent Data Analysis XXI, 2023
Éditeur: Springer, Cham
DOI: 10.1007/978-3-031-30047-9_19

Privacy Risk of Global Explainers

Auteurs: Francesca Naretto, Anna Monreale, Fosca Giannotti
Publié dans: Proceedings of the First International Conference on Hybrid Human-Artificial Intelligence, 2022
Éditeur: IOS Press
DOI: 10.3233/faia220206

Explaining Image Classifiers Generating Exemplars and Counter-Exemplars from Latent Representations

Auteurs: Guidotti Riccardo, Monreale Anna, Matwin Stan, Pedreschi Dino
Publié dans: Proceedings of the AAAI Conference on Artificial Intelligence, 2020
Éditeur: Association for the Advancement of Artificial Intelligence (AAAI)
DOI: 10.1609/aaai.v34i09.7116

Social Bias Probing: Fairness Benchmarking for Language Models

Auteurs: Marta Marchiori Manerba, Karolina Stanczak, Riccardo Guidotti, Isabelle Augenstein
Publié dans: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024, Page(s) 14653-14671
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/2024.emnlp-main.812

FairBelief - Assessing Harmful Beliefs in Language Models

Auteurs: Mattia Setzu, Marta Marchiori Manerba, Pasquale Minervini, Debora Nozza
Publié dans: Proceedings of the 4th Workshop on Trustworthy Natural Language Processing (TrustNLP 2024), 2024, Page(s) 27-39
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/2024.trustnlp-1.3

Explaining Any Time Series Classifier

Auteurs: Riccardo Guidotti, Anna Monreale, Francesco Spinnato, Dino Pedreschi, Fosca Giannotti
Publié dans: IEEE Second International Conference on Cognitive Machine Intelligence (CogMI), 2020, Page(s) 167-176
Éditeur: IEEE
DOI: 10.1109/cogmi50398.2020.00029

How routing strategies impact urban emissions

Auteurs: Giuliano Cornacchia, Matteo Böhm, Giovanni Mauro, Mirco Nanni, Dino Pedreschi, Luca Pappalardo
Publié dans: Proceedings of the 30th International Conference on Advances in Geographic Information Systems, Numéro SIGSPATIAL ’22 — November 1–4, 2022, Seattle, WA, USA, 2025, Page(s) 1-4, ISBN 978-1-4503-9529-8
Éditeur: ACM
DOI: 10.1145/3557915.3560977

Exemplars and Counterexemplars Explanations for Skin Lesion Classifiers

Auteurs: Carlo Metta, Riccardo Guidotti, Yuan Yin, Patrick Gallinari, Salvatore Rinzivillo
Publié dans: Volume 354: HHAI2022: Augmenting Human Intellect, 2022
Éditeur: IOS Press
DOI: 10.3233/faia220209

Data-Agnostic Local Neighborhood Generation

Auteurs: Riccardo Guidotti, Anna Monreale
Publié dans: 2020 IEEE International Conference on Data Mining (ICDM), 2020, Page(s) 1040-1045, ISBN 978-1-7281-8316-9
Éditeur: IEEE
DOI: 10.1109/icdm50108.2020.00122

User-driven counterfactual generator: a human centered exploration

Auteurs: Beretta I; Cappuccio E; Marchiori Manerba M
Publié dans: xAI-2023 - 1st World Conference on eXplainable Artificial, pp. 83–88, Lisbon, Portugal, 26-28/07/2023, Numéro 1, 2023, Page(s) 83-88, ISSN 1613-0073
Éditeur: CEUR (CEUR Workshop Proceedings)

Demo: an Interactive Visualization Combining Rule-Based and Feature Importance Explanations

Auteurs: Eleonora Cappuccio, Daniele Fadda, Rosa Lanzilotti, Salvatore Rinzivillo
Publié dans: Proceedings of the 15th Biannual Conference of the Italian SIGCHI Chapter, 2023, Page(s) 1-4
Éditeur: ACM
DOI: 10.1145/3605390.3610811

Understanding the impact of explanations on advice-taking: a user study for AI-based clinical Decision Support Systems

Auteurs: Cecilia Panigutti, Andrea Beretta, Fosca Giannotti, Dino Pedreschi
Publié dans: CHI '22: CHI Conference on Human Factors in Computing Systems, 2022, ISBN 9781450391573
Éditeur: Association for Computing Machinery
DOI: 10.1145/3491102.3502104

Evaluating the Privacy Exposure of Interpretable Global Explainers

Auteurs: Naretto Francesca, Monreale Anna, Giannotti Fosca
Publié dans: IEEE 4th International Conference on Cognitive Machine Intelligence (CogMI), 2022
Éditeur: IEEE
DOI: 10.1109/cogmi56440.2022.00012

FairShades: Fairness Auditing via Explainability in Abusive Language Detection Systems

Auteurs: Marchiori Manerba, Marta; Guidotti, Riccardo
Publié dans: 2021 IEEE Third International Conference on Cognitive Machine Intelligence (CogMI), 2021
Éditeur: IEEE Computer Society
DOI: 10.1109/cogmi52975.2021.00014

XAI in healthcare

Auteurs: Gezici G.; Metta C; Beretta A.; Pellungrini R.; Rinzivillo S.; Pedreschi D.; Giannotti F.
Publié dans: xAI 2024 - 2nd World Conference on eXplainable Artificial Intelligence, Numéro 1, 2024
Éditeur: CEUR-WS

Transparent Latent Space Counterfactual Explanations for Tabular Data

Auteurs: Bodria Francesco, Riccardo Guidotti, Fosca Giannotti, Dino Pedreschi
Publié dans: 2022
Éditeur: IEEE
DOI: 10.1109/dsaa54385.2022.10032407

Perspectives in Play: A Multi-Perspective Approach for More Inclusive NLP Systems

Auteurs: Benedetta Muscato, Lucia Passaro, Gizem Gezici, Fosca Giannotti
Publié dans: Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, 2025, Page(s) 9827-9835
Éditeur: International Joint Conferences on Artificial Intelligence Organization
DOI: 10.24963/ijcai.2025/1092

Predicting and Explaining Privacy Risk Exposure in Mobility Data

Auteurs: Francesca Naretto, Roberto Pellungrini, Anna Monreale, Franco Maria Nardini, Mirco Musolesi
Publié dans: Discovery Science Conference, 2020, Page(s) 403-418
Éditeur: Springer
DOI: 10.1007/978-3-030-61527-7_27

Multi-Perspective Stance Detection

Auteurs: Benedetta Muscato, Praveen Bushipaka, Gizem Gezici, Lucia Passaro, Fosca Giannotti
Publié dans: 2024
Éditeur: CEUR

Enhancing Echo State Networks with Gradient-based Explainability Methods

Auteurs: Francesco Spinnato, Andrea Cossu, Riccardo Guidotti, Andrea Ceni, Claudio Gallicchio, Davide Bacciu
Publié dans: ESANN 2024 proceesdings, 2024, Page(s) 17-22
Éditeur: Ciaco - i6doc.com
DOI: 10.14428/esann/2024.es2024-78

Explaining Black Box with Visual Exploration of Latent Space

Auteurs: Bodria, Francesco; Rinzivillo, Salvatore; Fadda, Daniele; Guidotti, Riccardo; Giannotti, Fosca; Pedreschi, Dino
Publié dans: Numéro 10, 2022
Éditeur: The Eurographics Association
DOI: 10.2312/evs.20221098

Boosting Synthetic Data Generation with Effective Nonlinear Causal Discovery

Auteurs: Martina Cinquini, Fosca Giannotti, Riccardo Guidotti
Publié dans: 2021 IEEE Third International Conference on Cognitive Machine Intelligence (CogMI), Numéro CogMI 2021 — December 13–16, 2021, Virtual Conference, 2022, Page(s) 54-63, ISBN 978-1-6654-4417-8
Éditeur: IEEE
DOI: 10.1109/cogmi52975.2021.00016

Explaining Crash Predictions on~Multivariate Time Series Data

Auteurs: Spinnato Francesco, Guidotti Riccardo, Nanni Mirco, Maccagnola Daniele, Paciello Giulia, Bencini Farina Antonio
Publié dans: Discovery Science 25th International Conference, DS 2022, Montpellier, France, October 10–12, 2022, Proceedings, 2022
Éditeur: Springer, Cham
DOI: 10.1007/978-3-031-18840-4_39

Requirements of eXplainable AI in Algorithmic Hiring

Auteurs: Andrea Beretta, Gianmario Ercoli, Alfonso Ferraro, Riccardo Guidotti, Andrea Iommi, Antonio Mastropietro, Anna Monreale, Daniela Rotelli, Salvatore Ruggieri
Publié dans: AIMMES 2024: AI bias – Measurements, Mitigation, Explanation Strategies (CEUR Workshop Proceedings, Vol. 3744), Numéro CEUR Workshop Proceedings, Volume 3744, 2024, Page(s) 75–86
Éditeur: CEUR-WS.org

Categorical Explaining Functors: Ensuring Coherence in Logical Explanations

Auteurs: Stefano Fioravanti, Francesco Giannini, Pietro Barbiero, Paolo Frazzetto, Roberto Confalonieri, Fabio Zanasi, Nicolò Navarin
Publié dans: Proceedings of the TwentySecond International Conference on Principles of Knowledge Representation and Reasoning, Numéro 22nd International Conference (KR2025), 2025, Page(s) 306-315, ISBN 978-1-956792-08-9
Éditeur: International Joint Conferences on Artificial Intelligence Organization
DOI: 10.24963/kr.2025/30

Ensemble of Counterfactual Explainers

Auteurs: Guidotti, Riccardo; Ruggieri, Salvatore
Publié dans: Discovery Science: 24th International Conference, DS 2021, 2021
Éditeur: ACM
DOI: 10.1007/978-3-030-88942-5_28

Prediction and Explanation of Privacy Risk on Mobility Data with Neural Networks

Auteurs: Francesca Naretto, Roberto Pellungrini, Franco Maria Nardini, Fosca Giannotti
Publié dans: ECML PKDD 2020 Workshops, 2020
Éditeur: Springer, Cham
DOI: 10.1007/978-3-030-65965-3_34

Beyond Headlines: A Corpus of Femicides News Coverage in Italian Newspapers

Auteurs: Eleonora Cappuccio, Benedetta Muscato, Laura Pollacci, Marta Marchiori Manerba, Clara Punzi, Chandana Mala, Margherita Lalli, Gizem Gezici, Michela Natilli, Fosca Giannotti
Publié dans: Proceedings of the Tenth Italian Conference on Computational Linguistics (CLiC-it 2024), Numéro 2024.clicit-1.21, 2024, Page(s) 171–181
Éditeur: CEUR Workshop Proceedings

Position Paper: On the Role of Abductive Reasoning in Semantic Image Segmentation.

Auteurs: Andrea Rafanelli; Stefania Costantini; Andrea Omicini
Publié dans: Numéro 1, 2022
Éditeur: CEUR-WS

An Overview of Recent Approaches to Enable Diversity in Large Language Models through Aligning with Human Perspectives

Auteurs: Muscato, Benedetta; Mala, Chandana Sree; Manerba M. M.; Gezici, Gizem; Giannotti, Fosca
Publié dans: CEUR Workshop Proceedings, Numéro 3, 2024
Éditeur: CEUR Workshop Proceedings

AUC-based Selective Classification

Auteurs: Pugnana Andrea, Ruggieri Salvatore
Publié dans: Proceedings of The 26th International Conference on Artificial Intelligence and Statistics, 2023
Éditeur: PMLR

Designing Shapelets for Interpretable Data-Agnostic Classification

Auteurs: Guidotti, Riccardo; Monreale, Anna
Publié dans: AIES '21: Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society, 2021
Éditeur: ACM
DOI: 10.1145/3461702.3462553

Explain and interpret few-shot learning

Auteurs: Fedele A.
Publié dans: xAI-2023 - 1st World Conference on eXplainable Artificial, pp. 233–240, Lisbon, Portugal, 26-28/06/2023, Numéro Vol. 3554, 2023, Page(s) 233–240
Éditeur: CEUR-WS (CEUR Workshop Proceedings)

Explanations Go Linear: Interpretable and Individual Latent Encoding for Post-hoc Explainability

Auteurs: Simone Piaggesi, Riccardo Guidotti, Fosca Giannotti, Dino Pedreschi
Publié dans: 2025
Éditeur: IEEE

Interpretable Latent Space to Enable Counterfactual Explanations

Auteurs: Francesco Bodria, Riccardo Guidotti, Fosca Giannotti, Dino Pedreschi
Publié dans: Lecture Notes in Artificial Intelligence (LNAI), 2022, ISSN 0302-9743
Éditeur: Springer Cham
DOI: 10.1007/978-3-031-18840-4_37

Doctor XAI: an ontology-based approach to black-box sequential data classification explanations

Auteurs: Cecilia Panigutti,Alan Perotti,Dino Pedreschi
Publié dans: FAT* '20: Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency, 2020, Page(s) 629–639
Éditeur: ACM
DOI: 10.1145/3351095.3372855

The ethical impact assessment of selling life insurance to titanic passengers

Auteurs: Gezici, Gizem; Mannari, Chiara; Orlandi, Lorenzo
Publié dans: HHAI-WS 2023 - Workshops at the Second International Conference on Hybrid Human-Artificial Intelligence, pp. 35–50, Munich, Germany, 26-27/06/2023, Numéro 20, 2023
Éditeur: CEUR-WS

Explaining Sentiment Classification with Synthetic Exemplars and Counter-Exemplars

Auteurs: Orestis Lampridis, Riccardo Guidotti, Salvatore Ruggieri
Publié dans: Lecture Notes in Computer Science, 2020
Éditeur: Springer
DOI: 10.1007/978-3-030-61527-7_24

Counterfactual and Prototypical Explanations for Tabular Data via Interpretable Latent Space

Auteurs: Simone Piaggesi, Francesco Bodria, Riccardo Guidotti, Fosca Giannotti, Dino Pedreschi
Publié dans: IEEE Access, Numéro 12, 2024, Page(s) 168983-169000, ISSN 2169-3536
Éditeur: Institute of Electrical and Electronics Engineers Inc.
DOI: 10.1109/access.2024.3496114

Fast, Interpretable, and Deterministic Time Series Classification With a Bag-of-Receptive-Fields

Auteurs: Francesco Spinnato, Riccardo Guidotti, Anna Monreale, Mirco Nanni
Publié dans: IEEE Access, Numéro 12, 2024, Page(s) 137893-137912, ISSN 2169-3536
Éditeur: Institute of Electrical and Electronics Engineers Inc.
DOI: 10.1109/access.2024.3464743

Topics in Selective Classification

Auteurs: Andrea Pugnana
Publié dans: Proceedings of the AAAI Conference on Artificial Intelligence, Numéro 37, 2023, Page(s) 16129-16130, ISSN 2374-3468
Éditeur: ACM
DOI: 10.1609/aaai.v37i13.26925

Inference through innovation processes tested in the authorship attribution task

Auteurs: Giulio Tani Raffaelli, Margherita Lalli, Francesca Tria
Publié dans: Communications Physics, Numéro 7, 2024, ISSN 2399-3650
Éditeur: Nature Communications Physics
DOI: 10.1038/s42005-024-01714-6

GLocalX - From Local to Global Explanations of Black Box AI Models

Auteurs: Mattia Setzu, Riccardo Guidotti, Anna Monreale, Franco Turini, Dino Pedreschi, Fosca Giannotti
Publié dans: Artificial Intelligence, Numéro 294, 2021, ISSN 0004-3702
Éditeur: Elsevier BV
DOI: 10.1016/j.artint.2021.103457

Improving trust and confidence in medical skin lesion diagnosis through explainable deep learning

Auteurs: Carlo Metta, Andrea Beretta, Riccardo Guidotti, Yuan Yin, Patrick Gallinari, Salvatore Rinzivillo, Fosca Giannotti
Publié dans: International Journal of Data Science and Analytics, 2023, ISSN 2364-415X
Éditeur: Springer Science+Business Media
DOI: 10.1007/s41060-023-00401-z

Explainable Authorship Identification in Cultural Heritage Applications

Auteurs: Mattia Setzu, Silvia Corbara, Anna Monreale, Alejandro Moreo, Fabrizio Sebastiani
Publié dans: Journal on Computing and Cultural Heritage, Numéro 17, 2024, Page(s) 1-23, ISSN 1556-4673
Éditeur: Association for Computing Machinary, Inc.
DOI: 10.1145/3654675

Deterministic, quenched, and annealed parameter estimation for heterogeneous network models

Auteurs: Marzio Di Vece, Diego Garlaschelli, Tiziano Squartini
Publié dans: Physical Review E, Numéro 108, 2023, Page(s) 054301, ISSN 2470-0045
Éditeur: American Physical Society (APS)
DOI: 10.1103/physreve.108.054301

Commodity-specific triads in the Dutch inter-industry production network

Auteurs: Marzio Di Vece, Frank P. Pijpers, Diego Garlaschelli
Publié dans: Scientific Reports, Numéro 14, 2024, ISSN 2045-2322
Éditeur: Nature Publishing Group
DOI: 10.1038/s41598-024-53655-3

Assessing Trustworthy AI in Times of COVID-19: Deep Learning for Predicting a Multiregional Score Conveying the Degree of Lung Compromise in COVID-19 Patients

Auteurs: Himanshi Allahabadi, Julia Amann, Isabelle Balot, Andrea Beretta, Charles Binkley, Jonas Bozenhard, Frederick Bruneault, James Brusseau, Sema Candemir, Luca Alessandro Cappellini, Subrata Chakraborty, Nicoleta Cherciu, Christina Cociancig, Megan Coffee, Irene Ek, Leonardo Espinosa-Leal, Davide Farina, Genevieve Fieux-Castagnet, Thomas Frauenfelder, Alessio Gallucci, Guya Giuliani, Adam Golda, Irmh
Publié dans: IEEE Transactions on Technology and Society, Numéro 3, 2023, Page(s) 272-289, ISSN 2637-6415
Éditeur: Institute of Electrical and Electronics Engineers (IEEE)
DOI: 10.1109/tts.2022.3195114

Matrix Profile-Based Interpretable Time Series Classifier

Auteurs: Riccardo Guidotti, Matteo D’Onofrio
Publié dans: Frontiers in Artificial Intelligence, Numéro 4, 2021, ISSN 2624-8212
Éditeur: Frontiers Media SA
DOI: 10.3389/frai.2021.699448

Understanding Any Time Series Classifier with a Subsequence-based Explainer

Auteurs: Francesco Spinnato, Riccardo Guidotti, Anna Monreale, Mirco Nanni, Dino Pedreschi, Fosca Giannotti
Publié dans: ACM Transactions on Knowledge Discovery from Data, Numéro 18, 2023, Page(s) 1-34, ISSN 1556-4681
Éditeur: Special Interest Group on Computer Graphics, Association for Computing Machinery
DOI: 10.1145/3624480

Shape-based Methods in Mobility Data Analysis: Effectiveness and Limitations

Auteurs: Cristiano Landi, Riccardo Guidotti
Publié dans: GeoInformatica, Numéro Volume 29,, 2024, Page(s) 999–1032, ISSN 1573-7624
Éditeur: Springer Science and Business Media LLC
DOI: 10.21203/rs.3.rs-5369626/v1

Explainable AI for Time Series Classification: A Review, Taxonomy and Research Directions

Auteurs: Andreas Theissler, Francesco Spinnato, Udo Schlegel, Riccardo Guidotti
Publié dans: IEEE Access (Volume: 10), 2022, ISSN 2169-3536
Éditeur: Institute of Electrical and Electronics Engineers Inc.
DOI: 10.1109/access.2022.3207765

Evaluating local explanation methods on ground truth

Auteurs: Guidotti, Riccardo
Publié dans: Artificial Intelligence, 2020, ISSN 0004-3702
Éditeur: Elsevier BV
DOI: 10.1016/j.artint.2020.103428

A Practical Approach to Causal Inference over Time

Auteurs: Martina Cinquini, Isacco Beretta, Salvatore Ruggieri, Isabel Valera
Publié dans: Proceedings of the AAAI Conference on Artificial Intelligence, Numéro 39, 2025, Page(s) 14832-14839, ISSN 2374-3468
Éditeur: Association for the Advancement of Artificial Intelligence (AAAI)
DOI: 10.1609/aaai.v39i14.33626

SafeGen: safeguarding privacy and fairness through a genetic method

Auteurs: Martina Cinquini, Marta Marchiori Manerba, Federico Mazzoni, Francesca Pratesi, Riccardo Guidotti
Publié dans: Machine Learning, Numéro 114, 2025, Page(s) 227, ISSN 0885-6125
Éditeur: Kluwer Academic Publishers
DOI: 10.1007/s10994-025-06835-9

Advancing Dermatological Diagnostics: Interpretable AI for Enhanced Skin Lesion Classification

Auteurs: Carlo Metta, Andrea Beretta, Riccardo Guidotti, Yuan Yin, Patrick Gallinari, Salvatore Rinzivillo, Fosca Giannotti
Publié dans: Diagnostics, Numéro 14, 2024, Page(s) 753, ISSN 2075-4418
Éditeur: Diagnostics
DOI: 10.3390/diagnostics14070753

Occlusion-Based Explanations in Deep Recurrent Models for Biomedical Signals

Auteurs: Michele Resta, Anna Monreale, Davide Bacciu
Publié dans: Entropy, Numéro 8, 2021, ISSN 1099-4300
Éditeur: Multidisciplinary Digital Publishing Institute (MDPI)
DOI: 10.3390/e23081064

Explainable Artificial Intelligence (XAI) 2.0: A manifesto of open challenges and interdisciplinary research directions

Auteurs: Luca Longo, Mario Brcic, Federico Cabitza, Jaesik Choi, Roberto Confalonieri, Javier Del Ser, Riccardo Guidotti, Yoichi Hayashi, Francisco Herrera, Andreas Holzinger, Richard Jiang, Hassan Khosravi, Freddy Lecue, Gianclaudio Malgieri, Andrés Páez, Wojciech Samek, Johannes Schneider, Timo Speith, Simone Stumpf
Publié dans: Information Fusion, Numéro 106, 2024, Page(s) 102301, ISSN 1566-2535
Éditeur: Elsevier BV
DOI: 10.1016/j.inffus.2024.102301

Counterfactual explanations and how to find them: literature review and benchmarking

Auteurs: Riccardo Guidotti
Publié dans: Data Mining and Knowledge Discovery, 2022, ISSN 1384-5810
Éditeur: Kluwer Academic Publishers
DOI: 10.1007/s10618-022-00831-6

Evaluating the Privacy Exposure of Interpretable Global and Local Explainers

Auteurs: Francesca Naretto, Anna Monreale, Fosca Giannotti
Publié dans: Evaluating the Privacy Exposure of Interpretable Global and Local Explainers, Numéro 18(2), 2025, Page(s) 67–93, ISSN 1888-5063
Éditeur: Institut d'Investigacio en Intel-ligencia Artificial - Consejo Superior Investigaciones Cientificas (IIIA-CSIC)

Counterfactual Situation Testing: From Single to Multidimensional Discrimination

Auteurs: Jose M. Alvarez, Salvatore Ruggieri
Publié dans: Journal of Artificial Intelligence Research, Numéro 82, 2025, Page(s) 2279-2323, ISSN 1076-9757
Éditeur: Morgan Kaufmann Publishers, Inc.
DOI: 10.1613/jair.1.17935

Exemplars and Counterexemplars Explanations for Image Classifiers, Targeting Skin Lesion Labeling

Auteurs: Metta, Carlo; Guidotti, Riccardo; Yin, Yuan; Gallinari, Patrick; Rinzivillo, Salvatore
Publié dans: 2021 IEEE Symposium on Computers and Communications (ISCC), 2021, ISSN 2642-7389
Éditeur: IEEE
DOI: 10.1109/iscc53001.2021.9631485

The explanation dialogues: an expert focus study to understand requirements towards explanations within the GDPR

Auteurs: Laura State, Alejandra Bringas Colmenarejo, Andrea Beretta, Salvatore Ruggieri, Franco Turini, Stephanie Law
Publié dans: Artificial Intelligence and Law, 2025, ISSN 0924-8463
Éditeur: Kluwer Academic Publishers
DOI: 10.1007/s10506-024-09430-w

Analysis of exposome and genetic variability suggests stress as a major contributor for development of pancreatic ductal adenocarcinoma

Auteurs: Giulia Peduzzi, Alessio Felici, Roberto Pellungrini, Francesca Giorgolo, Riccardo Farinella, Manuel Gentiluomo, Andrea Spinelli, Gabriele Capurso, Anna Monreale, Federico Canzian, Marco Calderisi, Daniele Campa
Publié dans: Digestive and Liver Disease, Numéro 56, 2024, Page(s) 1054-1063, ISSN 1590-8658
Éditeur: W. B. Saunders Co., Ltd.
DOI: 10.1016/j.dld.2023.10.015

FairLens: Auditing black-box clinical decision support systems

Auteurs: Cecilia Panigutti, Alan Perotti, André Panisson, Paolo Bajardi, Dino Pedreschi
Publié dans: Information Processing & Management, Numéro 58, 2021, ISSN 0306-4573
Éditeur: Pergamon Press Ltd.
DOI: 10.1016/j.ipm.2021.102657

The ALTAI checklist as a tool to assess ethical and legal implications for a trustworthy AI development in education

Auteurs: Andrea Fedele, Clara Punzi, Stefano Tramacere
Publié dans: Computer Law & Security Review, Numéro 53, 2025, Page(s) 105986, ISSN 2212-473X
Éditeur: Elsevier BV
DOI: 10.1016/j.clsr.2024.105986

Factual and Counterfactual Explanations for Black Box Decision Making

Auteurs: Guidotti, R., Monreale, A., Giannotti, F., Pedreschi, D., Ruggieri, S., Turini, F.
Publié dans: IEEE Intelligent Systems, 2019, Page(s) 14 - 23, ISSN 1541-1672
Éditeur: Institute of Electrical and Electronics Engineers
DOI: 10.1109/mis.2019.2957223

Towards Transparent Healthcare: Advancing Local Explanation Methods in Explainable Artificial Intelligence

Auteurs: Carlo Metta, Andrea Beretta, Roberto Pellungrini, Salvatore Rinzivillo, Fosca Giannotti
Publié dans: Bioengineering, Numéro 11, 2024, Page(s) 369, ISSN 2306-5354
Éditeur: Bioengineering
DOI: 10.3390/bioengineering11040369

A Survey on Graph Counterfactual Explanations: Definitions, Methods, Evaluation, and Research Challenges

Auteurs: Mario Alfonso Prado-Romero, Bardh Prenkaj, Giovanni Stilo, Fosca Giannotti
Publié dans: ACM Computing Surveys, Numéro 56, 2025, Page(s) 1-37, ISSN 0360-0300
Éditeur: Association for Computing Machinary, Inc.
DOI: 10.1145/3618105

Effects of Route Randomization on Urban Emissions

Auteurs: Giuliano Cornacchia, Mirco Nanni, Dino Pedreschi, Luca Pappalardo
Publié dans: SUMO Conference Proceedings, Numéro 4, 2024, Page(s) 75-87, ISSN 2750-4425
Éditeur: TIB Open Publishing
DOI: 10.52825/scp.v4i.217

Co-design of human-centered, explainable AI for clinical decision support

Auteurs: Panigutti, C., Beretta, A., Fadda, D., Giannotti, F., Pedreschi, D., Perotti, A., Rinzivillo, S.
Publié dans: ACM Transactions on Interactive Intelligent Systems, 2023, ISSN 2160-6455
Éditeur: Association for Computing Machinery (ACM)
DOI: 10.1145/3587271

Stable and actionable explanations of black-box models through factual and counterfactual rules

Auteurs: Riccardo Guidotti, Anna Monreale, Salvatore Ruggieri, Francesca Naretto, Franco Turini, Dino Pedreschi, Fosca Giannotti
Publié dans: Data Mining and Knowledge Discovery, Numéro 38, 2024, Page(s) 2825-2862, ISSN 1384-5810
Éditeur: Kluwer Academic Publishers
DOI: 10.1007/s10618-022-00878-5

Benchmarking and survey of explanation methods for black box models

Auteurs: Francesco Bodria, Fosca Giannotti, Riccardo Guidotti, Francesca Naretto, Dino Pedreschi, Salvatore Rinzivillo
Publié dans: Data Mining and Knowledge Discovery, Numéro Volume 37 Numéro 3, May 2023, 2023, ISSN 1384-5810
Éditeur: Kluwer Academic Publishers
DOI: 10.1007/s10618-023-00933-9

Understanding peace through the world news

Auteurs: Voukelatou Vasiliki, Miliou Ioanna, Giannotti Fosca, Pappalardo Luca
Publié dans: EPJ Data Science, 2022, ISSN 2193-1127
Éditeur: Springer Science and Business Media LLC
DOI: 10.1140/epjds/s13688-022-00315-z

Generative Model for Decision Trees

Auteurs: Riccardo Guidotti, Anna Monreale, Mattia Setzu, Giulia Volpi
Publié dans: Proceedings of the AAAI Conference on Artificial Intelligence, Numéro 38, 2024, Page(s) 21116-21124, ISSN 2374-3468
Éditeur: AAAI Press
DOI: 10.1609/aaai.v38i19.30104

An Interpretable Data-Driven Unsupervised Approach for the Prevention of Forgotten Items

Auteurs: Luca Corbucci, Javier Alejandro Borges Legrottaglie, Francesco Spinnato, Anna Monreale, Riccardo Guidotti
Publié dans: Frontiers in Artificial Intelligence and Applications, ECAI 2025, 2025
Éditeur: IOS Press
DOI: 10.3233/faia250912

Explaining Black-Boxes in Federated Learning

Auteurs: Luca Corbucci, Riccardo Guidotti, Anna Monreale
Publié dans: Communications in Computer and Information Science, Explainable Artificial Intelligence, 2024, Page(s) 151-163
Éditeur: Springer Nature Switzerland
DOI: 10.1007/978-3-031-44067-0_8

A Frank System for Co-Evolutionary Hybrid Decision-Making

Auteurs: Federico Mazzoni, Riccardo Guidotti, Alessio Malizia
Publié dans: Lecture Notes in Computer Science, Advances in Intelligent Data Analysis XXII, 2024, Page(s) 236-248
Éditeur: Springer Nature Switzerland
DOI: 10.1007/978-3-031-58553-1_19

Interpretable Instance-Based Learning Through Pairwise Distance Trees

Auteurs: Andrea Fedele, Alessio Cascione, Riccardo Guidotti, Cristiano Landi
Publié dans: Lecture Notes in Computer Science, Machine Learning and Knowledge Discovery in Databases. Research Track, Numéro 15126, 2025, Page(s) 3-21, ISBN 978-3-032-06078-5
Éditeur: Springer Nature Switzerland
DOI: 10.1007/978-3-032-06078-5_1

Embracing Diversity: A Multi-Perspective Approach with Soft Labels

Auteurs: Benedetta Muscato, Praveen Bushipaka, Gizem Gezici, Lucia Passaro, Fosca Giannotti, Tommaso Cucinotta
Publié dans: Frontiers in Artificial Intelligence and Applications, HHAI 2025, Numéro Volume 408 (FAIA), 2025, ISBN 978-1-64368-611-0
Éditeur: IOS Press
DOI: 10.3233/faia250654

Towards Building a Trustworthy RAG-Based Chatbot for the Italian Public Administration

Auteurs: Chandana Sree Mala, Christian di Maio, Mattia Proietti, Gizem Gezici, Fosca Giannotti, Stefano Melacci, Alessandro Lenci, Marco Gori
Publié dans: Frontiers in Artificial Intelligence and Applications, HHAI 2025, Numéro Volume 408 (FAIA), 2025, ISBN 978-1-64368-611-0
Éditeur: IOS Press
DOI: 10.3233/faia250637

Causality-Aware Local Interpretable Model-Agnostic Explanations

Auteurs: Martina Cinquini, Riccardo Guidotti
Publié dans: Communications in Computer and Information Science, Explainable Artificial Intelligence, 2024, Page(s) 108-124
Éditeur: Springer Nature Switzerland
DOI: 10.1007/978-3-031-63800-8_6

Group Explainability Through Local Approximation

Auteurs: Mattia Setzu, Riccardo Guidotti, Dino Pedreschi, Fosca Giannotti
Publié dans: Frontiers in Artificial Intelligence and Applications, ECAI 2025, 2025
Éditeur: IOS Press
DOI: 10.3233/faia250902

The Importance of Time in Causal Algorithmic Recourse

Auteurs: Isacco Beretta, Martina Cinquini
Publié dans: Communications in Computer and Information Science, Explainable Artificial Intelligence, 2023, Page(s) 283-298
Éditeur: Springer Nature Switzerland
DOI: 10.1007/978-3-031-44064-9_16

An Interactive Interface for Feature Space Navigation

Auteurs: Eleonora Cappuccio, Isacco Beretta, Marta Marchiori Manerba, Salvatore Rinzivillo
Publié dans: Frontiers in Artificial Intelligence and Applications, HHAI 2024: Hybrid Human AI Systems for the Social Good, 2024
Éditeur: IOS Press
DOI: 10.3233/faia240184

Balancing Fairness and Interpretability in Clustering with FairParTree

Auteurs: Cristiano Landi, Alessio Cascione, Marta Marchiori Manerba, Riccardo Guidotti
Publié dans: Communications in Computer and Information Science, Explainable Artificial Intelligence, Numéro 2185, 2025, Page(s) 104-127, ISBN 978-3-032-08324-1
Éditeur: Springer Nature Switzerland
DOI: 10.1007/978-3-032-08324-1_5

Interpretable Data Partitioning Through Tree-Based Clustering Methods

Auteurs: Riccardo Guidotti, Cristiano Landi, Andrea Beretta, Daniele Fadda, Mirco Nanni
Publié dans: Lecture Notes in Computer Science, Discovery Science, 2024, Page(s) 492-507
Éditeur: Springer Nature Switzerland
DOI: 10.1007/978-3-031-45275-8_33

Exploring Large Language Models Capabilities to Explain Decision Trees

Auteurs: Paulo Bruno Serafim, Pierluigi Crescenzi, Gizem Gezici, Eleonora Cappuccio, Salvatore Rinzivillo, Fosca Giannotti
Publié dans: Frontiers in Artificial Intelligence and Applications, HHAI 2024: Hybrid Human AI Systems for the Social Good, 2024
Éditeur: IOS Press
DOI: 10.3233/faia240183

Text to Time Series Representations: Towards Interpretable Predictive Models

Auteurs: Mattia Poggioli, Francesco Spinnato, Riccardo Guidotti
Publié dans: Lecture Notes in Computer Science, Discovery Science, 2024, Page(s) 230-245
Éditeur: Springer Nature Switzerland
DOI: 10.1007/978-3-031-45275-8_16

Ensemble Counterfactual Explanations for Churn Analysis

Auteurs: Samuele Tonati, Marzio Di Vece, Roberto Pellungrini, Fosca Giannotti
Publié dans: Lecture Notes in Computer Science, Discovery Science, Numéro 01/01/2025, 2025, Page(s) 332-347
Éditeur: Springer Nature Switzerland
DOI: 10.1007/978-3-031-78980-9_21

Interpretable and Fair Mechanisms for Abstaining Classifiers

Auteurs: Daphne Lenders, Andrea Pugnana, Roberto Pellungrini, Toon Calders, Dino Pedreschi, Fosca Giannotti
Publié dans: Lecture Notes in Computer Science, Machine Learning and Knowledge Discovery in Databases. Research Track, 2024, Page(s) 416-433
Éditeur: Springer Nature Switzerland
DOI: 10.1007/978-3-031-70368-3_25

Deriving a Single Interpretable Model by Merging Tree-Based Classifiers

Auteurs: Valerio Bonsignori, Riccardo Guidotti, Anna Monreale
Publié dans: Discovery Science, 2021, ISSN 0302-9743
Éditeur: Springer International Publishing
DOI: 10.1007/978-3-030-88942-5_27

EXPHLOT: EXplainable Privacy Assessment for Human LOcation Trajectories

Auteurs: Francesca Naretto, Roberto Pellungrini, Salvatore Rinzivillo, Daniele Fadda
Publié dans: Lecture Notes in Computer Science, Discovery Science, 2024, Page(s) 325-340
Éditeur: Springer Nature Switzerland
DOI: 10.1007/978-3-031-45275-8_22

Unsupervised and Interpretable Detection of User Personalities in Online Social Networks

Auteurs: Alessio Cascione, Laura Pollacci, Riccardo Guidotti
Publié dans: Communications in Computer and Information Science, Explainable Artificial Intelligence, Numéro 2186, 2025, Page(s) 162-179, ISBN 978-3-032-08327-2
Éditeur: Springer Nature Switzerland
DOI: 10.1007/978-3-032-08327-2_8

Principles of Explainable Artificial Intelligence

Auteurs: Riccardo Guidotti, Anna Monreale, Dino Pedreschi, Fosca Giannotti
Publié dans: Explainable AI Within the Digital Transformation and Cyber Physical Systems, 2021, Page(s) 9-31, ISBN 978-3-030-76409-8
Éditeur: Springer, Cham
DOI: 10.1145/3461702.3462553

Explaining Socio-Demographic and Behavioral Patterns of Vaccination Against the Swine Flu (H1N1) Pandemic

Auteurs: Clara Punzi, Aleksandra Maslennikova, Gizem Gezici, Roberto Pellungrini, Fosca Giannotti
Publié dans: Communications in Computer and Information Science, Explainable Artificial Intelligence, 2024, Page(s) 621-635
Éditeur: Springer Nature Switzerland
DOI: 10.1007/978-3-031-44067-0_31

FLocalX - Local to Global Fuzzy Explanations for Black Box Classifiers

Auteurs: Guillermo Fernandez, Riccardo Guidotti, Fosca Giannotti, Mattia Setzu, Juan A. Aledo, Jose A. Gámez, Jose M. Puerta
Publié dans: Lecture Notes in Computer Science, Advances in Intelligent Data Analysis XXII, 2024, Page(s) 197-209
Éditeur: Springer Nature Switzerland
DOI: 10.1007/978-3-031-58553-1_16

Declarative Reasoning on Explanations Using Constraint Logic Programming

Auteurs: Laura State, Salvatore Ruggieri, Franco Turini
Publié dans: Lecture Notes in Computer Science, Logics in Artificial Intelligence, 2023, Page(s) 132-141
Éditeur: Springer Nature Switzerland
DOI: 10.1007/978-3-031-43619-2_10

Semantic Enrichment of Explanations of AI Models for Healthcare

Auteurs: Luca Corbucci, Anna Monreale, Cecilia Panigutti, Michela Natilli, Simona Smiraglio, Dino Pedreschi
Publié dans: Lecture Notes in Computer Science, Discovery Science, 2024, Page(s) 216-229
Éditeur: Springer Nature Switzerland
DOI: 10.1007/978-3-031-45275-8_15

MASCOTS: Model-Agnostic Symbolic COunterfactual Explanations for Time Series

Auteurs: Dawid Płudowski, Francesco Spinnato, Piotr Wilczyński, Krzysztof Kotowski, Evridiki Vasileia Ntagiou, Riccardo Guidotti, Przemysław Biecek
Publié dans: Lecture Notes in Computer Science, Machine Learning and Knowledge Discovery in Databases. Research Track, Numéro 15126, 2025, Page(s) 94-112, ISBN 978-3-032-06078-5
Éditeur: Springer Nature Switzerland
DOI: 10.1007/978-3-032-06078-5_6

Reason to Explain: Interactive Contrastive Explanations (REASONX)

Auteurs: Laura State, Salvatore Ruggieri, Franco Turini
Publié dans: Communications in Computer and Information Science, Explainable Artificial Intelligence, 2023, Page(s) 421-437
Éditeur: Springer Nature Switzerland
DOI: 10.1007/978-3-031-44064-9_22

Explainable AI in Time-Sensitive Scenarios: Prefetched Offline Explanation Model

Auteurs: Fabio Michele Russo, Carlo Metta, Anna Monreale, Salvatore Rinzivillo, Fabio Pinelli
Publié dans: Lecture Notes in Computer Science, Discovery Science, 2025, Page(s) 167-182
Éditeur: Springer Nature Switzerland
DOI: 10.1007/978-3-031-78980-9_11

Mathematical Foundation of Interpretable Equivariant Surrogate Models

Auteurs: Jacopo Joy Colombini, Filippo Bonchi, Francesco Giannini, Fosca Giannotti, Roberto Pellungrini, Patrizio Frosini
Publié dans: Communications in Computer and Information Science, Explainable Artificial Intelligence, Numéro 2185, 2025, Page(s) 294-318, ISBN 978-3-032-08324-1
Éditeur: Springer Nature Switzerland
DOI: 10.1007/978-3-032-08324-1_13

Data-Agnostic Pivotal Instances Selection for Decision-Making Models

Auteurs: Alessio Cascione, Mattia Setzu, Riccardo Guidotti
Publié dans: Lecture Notes in Computer Science, Machine Learning and Knowledge Discovery in Databases. Research Track, 2024, Page(s) 367-386
Éditeur: Springer Nature Switzerland
DOI: 10.1007/978-3-031-70341-6_22

DINE: Dimensional Interpretability of Node Embeddings

Auteurs: Simone Piaggesi, Megha Khosla, André Panisson, Avishek Anand
Publié dans: IEEE Transactions on Knowledge and Data Engineering, Numéro 36, 2024, Page(s) 7986-7997, ISSN 1041-4347
Éditeur: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tkde.2024.3425460

Explaining Siamese networks in few-shot learning

Auteurs: Andrea Fedele, Riccardo Guidotti, Dino Pedreschi
Publié dans: Machine Learning, Numéro 113, 2024, Page(s) 7723-7760, ISSN 0885-6125
Éditeur: Kluwer Academic Publishers
DOI: 10.1007/s10994-024-06529-8

Mapping the landscape of ethical considerations in explainable AI research

Auteurs: Luca Nannini, Marta Marchiori Manerba, Isacco Beretta
Publié dans: Ethics and Information Technology, Numéro 26, 2024, ISSN 1388-1957
Éditeur: Kluwer Academic Publishers
DOI: 10.1007/s10676-024-09773-7

Drifting explanations in continual learning

Auteurs: Andrea Cossu, Francesco Spinnato, Riccardo Guidotti, Davide Bacciu
Publié dans: Neurocomputing, Numéro 597, 2024, Page(s) 127960, ISSN 0925-2312
Éditeur: Elsevier BV
DOI: 10.1016/j.neucom.2024.127960

Opening the black box: a primer for anti-discrimination

Auteurs: Ruggieri Salvatore, Giannotti Fosca, Guidotti Riccardo, Monreale Anna, Pedreschi Dino, Turini Franco
Publié dans: ANNUARIO DI DIRITTO COMPARATO E DI STUDI LEGISLATIVI, 2021, ISSN 2039-9871
Éditeur: Esi - Edizioni scientifiche Italiane

Publications

Partager cette page Partager cette page sur les réseaux sociaux

Télécharger Télécharger le contenu de la page