Explainable Artificial Intelligence

Period of duration of course
Course info
Number of course hours
Number of hours of lecturers of reference
Number of hours of supplementary teaching

Modalità esame



View lecturer details


Basic notions of machine learning


Black box AI systems for automated decision-making, often based on machine learning over (big) data, map a user’s features into a class or a score without exposing the reasons why. This is problematic not only for the lack of transparency but also for possible biases inherited by the algorithms from human prejudices and collection artifacts hidden in the training data, which may lead to unfair or wrong decisions. The future of AI lies in enabling people to collaborate with machines to solve complex problems. Like any efficient collaboration, this requires good communication, trust, clarity and understanding.

Explainable AI addresses such challenges and for years different AI communities have studied such topics, leading to different definitions, evaluation protocols, motivations, and results. 

This (20 hours+10 hours of hands-on laboratory) course provides a reasoned introduction to the work of Explainable AI (XAI) to date. It surveys the literature with a focus on post-hoc and by-design approaches.  

We motivate the needs of XAI in real-world and large-scale applications, while presenting state-of-the-art techniques and best practices, as well as discussing the many open challenges. An XAI platform with a collection of many of the recently proposed algorithms will be presented on specific use cases and it will be possible to familiarize with some of the methods.

The course is organized as follows in three modules: i) an introductory one providing motivations, main concepts and main methods; ii) an advanced one where the students will actively participate to monograph topics with readings interleaved with interventions of international scholars working on the sector; iii) an hands-on module where the students will be introduced to the usage on XAI methods.

The period is between January 8th and February 13th: two lectures and a laboratory session for the week.

The course will also provide one open lab to support students for project execution (support for project execution) (10 hours) Didattica Integrativa

The period is between December 11 and February 28.  

Scheduling: Monday: 14-16 Tuesday 11-13 Aula Bianchi Scienze, Tuesday 16-18 (TBC) Aula Bianchi Scienze,

form January 8

1) Module1 (10 hours):  Crush course on XAI.

  1.  Motivation for XAI: Why explanation and What is an explanation. The taxonomy of XAI methods for Machine Learnin
  2. Overview post-hoc explanation methods
  3. Overview of transparent by-design methods

2) Module2 (10 hours): Advanced Concepts

  1. Counterfactual explanations
  2.  Explaining by design – argumentation and knowledge graph –
  3.  Explaining by design & Global Explainer: on the integration of symbolic and sub-symbolic
  4.  Interactive XAI – the new research challenges in XAI
  5.  Student seminars on advanced topics

3)  Module3 (10 hours):  Hands-on: on XAI methods.  (By Roberto Pellungrini) interleaved with Module1

  1.       The students will be introduced to python library of XAI-Lib methods for tabular data (4h)       
  2.      The students will be introduced to python library of XAI methods for images data (4h)
  3.       The students will be introduced to some global explanation method (2h)

Exam:     Student seminars and project presentation 

Obiettivi formativi

O1: This course provides a reasoned introduction to the work of Explainable AI (XAI) to date, and surveys the literature with a focus on machine learning and symbolic AI-related approaches.

O2: To familiarize with many of the recently proposed methods and relative algorithms on specific use cases

Riferimenti bibliografici

1)     Tim Miller Explanaition in Artificial Intelligence: Insight from Social Science

2)     Causal Interpretability Survey, 2018, R.  Moraffah,  M.  Karami,  R.  Guo,  A.  Raglin,  &  H.  Liu (2020).   Causal  interpretability for machine learning - problems,  methods and evaluation. SIGKDD Explorations, 22(1):18–33. www.kdd.org/exploration/Causal_Explainability.pdf

3)     Counterfactual Explanation Survey - S. Verma, J. P. Dickerson, K. Hines (2020). Counterfactual Explanations for Machine Learning: A Review. CoRR abs/2010.10596

4)     Symbolic Techniques for XAI Survey .R. Calegari, G. Ciatto, A. Omicini (2020). On the integration of symbolic and sub-symbolic techniques for XAI: A survey. Intelligenza Artificiale 14(1): 7-32

5)     Guidotti, R., Monreale, A., Ruggieri, S., Turini, F., Giannotti, F., & Pedreschi, D. (2018). A survey of methods for explaining black box models. ACM Computing Surveys (CSUR), 51(5), 93

6)     Guidotti, R. Counterfactual explanations and how to find them: literature review and benchmarking. Data Min Knowl Disc (2022). https://doi.org/10.1007/s10618-022-00831-6

7)     Bodria, F., Giannotti, F., Guidotti, R. et al. Benchmarking and survey of explanation methods for black box models. Data Min Knowl Disc 37, 1719–1778 (2023).

8)     Mario Alfonso Prado-Romero, Bardh Prenkaj, Giovanni Stilo, Fosca Giannotti , A Survey on Graph Counterfactual Explanations: Definitions, Methods, Evaluation, and Research Challenges ACM Computing Surveys