Special Session

Advances on eXplainable Artificial Intelligence

Organized by: Jose M. Alonso, Ciro Castiello, Corrado Mencar, Luis Magdalena, Shang-Ming Zhou

Venue: FUZZ-IEEE 2021 conference, Luxembourg, July 11-14, 2021

This Special Session is supported by the IEEE-CIS Task Force on Explainable Fuzzy Systems

NOTE: due to covid-19, the final decision by IEEE CIS is for Fuzz-IEEE 2021 to go ahead as a fully virtual conference

The Conference Program is online (CEST)

Session Mon-S-A2: Advances on Explainable Artificial Intelligence-I

Monday, July 12, 9:00AM-10:40AM, Room: Stream 2, Chair: Jose M. Alonso, Luis Magdalena and Corrado Mencar

9:00AM. Explainable Classification Methods for Fish Species Detection Using Hydroacoustic Data [#3]

Lucas Bonifacio, Giancarlo Lucca, Gracaliz Dimuro, Eduardo Borges, Leonardo Emmendorfer and Stefan Weigert (Federal Univ. of Rio Grande, Brazil; UPNA & Federal Univ. of Rio Grande, Spain)

9:20AM. Actionable XAI for the Fuzzy Integral [#11]

Bryce Murray, Derek Anderson and Timothy Havens (University of Missouri, United States; Michigan Technological University, United States)

9:40AM. Generation of Textual Explanations in XAI: the Case of Semantic Annotation [#19]

Jean-Philippe Poli, Wassila Ouerdane and Regis Pierrard (CEA List, France; CentraleSupelec, France; CEA List, French Southern Territories)

10:00AM. Meta-Fuzzy Items for Fuzzy Association Rules [#161]

Carmen Biedma-Rdguez, Maria Jose Gacto, Rafael Alcala and Jesus Alcala-Fdez (University of Granada, Spain; University of Jaen, Spain)

10:20AM. An Explainable Approach for Car Driver Identification [#138]

Gionatan Gallo, Mario Luca Bernardi, Marta Cimitile and Pietro Ducange (Department of Information Engineering, University of Pisa, Pisa, Italy; Unisannio University, Benevento, Italy; UnitelmaSapienza University, Roma, Italy)

Session Mon-S-B2: Advances on Explainable Artificial Intelligence-II

Monday, July 12, 11:00AM-12:40PM, Room: Stream 2, Chair: Corrado Mencar, Jose M. Alonso, and Luis Magdalena

11:00AM. XAI Models for Quality of Experience Prediction in Wireless Networks [#250]

Alessandro Renda, Pietro Ducange, Gionatan Gallo and Francesco Marcelloni (University of Pisa, Italy)

11:20AM. Bayesian Pruned Random Rule Foams for XAI [#74]

Akash Panda and Bart Kosko (University of Southern California, United States)

11:40AM. Min-max inference for Possibilistic Rule-Based System [#266]

Ismail Baaj, Jean-Philippe Poli, Wassila Ouerdane and Nicolas Maudet (CEA, Sorbonne Universite, France; CEA, France; CentraleSupelec, France; Sorbonne Universite, France)

12:00PM. A Framework for Analyzing Fairness, Accountability, Transparency and Ethics: A Use-case in Banking Services [#144]

Ettore Mariotti, Jose Maria Alonso and Roberto Confalonieri (CiTIUS – Universidade de Santiago de Compostela, Spain; Faculty of Computer Science – Free University of Bozen-Bolzano, Italy)

12:20PM. Descriptive Stability of Fuzzy Rule-Based Systems [#155]

Corrado Mencar and Ciro Castiello (Universita degli Studi di Bari Aldo Moro, Italy

Scope

In the era of the Internet of Things and Big Data, data scientists are required to extract valuable knowledge from the given data. They first analyze, cure and pre-process data. Then, they apply Artificial Intelligence (AI) techniques to automatically extract knowledge from data.

Our focus is on fuzzy-grounded knowledge representation and how to enhance human-machine interaction. As remarked in the last challenge stated by the USA Defense Advanced Research Projects Agency (DARPA), "even though current AI systems offer many benefits in many applications, their effectiveness is limited by a lack of explanation ability when interacting with humans". Accordingly, users without a strong background on AI, require a new generation of explainable AI systems (XAI in short). They are expected to naturally interact with humans, thus providing comprehensible explanations of decisions automatically made. Thus, the goal of this special session is to discuss and disseminate the most recent advancements focused on XAI. The session goes a step ahead in the way towards XAI and it is supported by the IEEE-CIS Task Force on Explainable Fuzzy Systems and the H2020 MSCA-ITN-2019 NL4XAI project.

The aim of this session is to offer an opportunity for researchers and practitioners to identify new promising research directions on XAI and to provide a forum to disseminate and discuss XAI, with special attention to Explainable Fuzzy Systems.

Three main XAI challenges are to be addressed:

Designing explainable models.
Building explanation interfaces.
Measuring explainability.

We organized previously some related events: XAI@WCCI2020, XAI@INLG2019, XAI@FUZZ-IEEE2019, XAI@IEEESMC, IPMU2018, FUZZ-IEEE2017, IFSA-EUSFLAT2015, EUSFLAT 2013, IEEEWCCI 2012, IEEEWCCI 2010, and joint IFSA-EUSFLAT 2009.

Topics

Explainable Computational Intelligence
Theoretical Aspects of Interpretability
Dimensions of Interpretability: Readability versus Understandability
Learning Methods for Interpretable Systems and Models
Interpretability Evaluation and Improvements
Models for Explainable Recommendations
Design Issues
Applications of XAI Systems

Interpretable Machine Learning
Interpretable Fuzzy Systems
Relations between Interpretability and other Criteria (such as Accuracy, Stability, Relevance, etc.)
Explainable Agents
Self-explanatory Decision-Support Systems
Argumentation Theory for XAI
Natural Language Generation for XAI
Human-Machine Interaction for XAI

Notes

Papers submitted for this special session are to be peer-reviewed with the same criteria used for the rest of contributed papers to the general track of the conference. As a result, all accepted papers will be included in the proceedings of the FUZZ-IEEE 2021. If you are interested in taking part in this special session, please submit your paper directly through the FUZZ-IEEE2021 submission website selecting the option (instructions for authors):

"Main research topic": Advances on Explainable Artificial Intelligence