Special Issue

Explainable and Trustworthy Artificial Intelligence

Journal: IEEE Computational Intelligence Magazine

Editors: Jose M. Alonso, Corrado Mencar, Hisao Ishibuchi

Already Published:

J.M. Alonso-Moral, C. Mencar, H. Ishibuchi, "Explainable and Trustworthy Artificial Intelligence [Guest Editorial]", IEEE Computational Intelligence Magazine, 17(1):14-15, 2022
M. Kiani, J. Andreu-Perez, H. Hagras, S. Rigato, M.L. Filippetti, "Towards Understanding Human Functional Brain Development With Explainable Artificial Intelligence: Challenges and Perspectives", IEEE Computational Intelligence Magazine, 17(1):16-33, 2022
A. Ghods, D.J. Cook, "PIP: Pictorial Interpretable Prototype Learning for Time Series Classification", IEEE Computational Intelligence Magazine, 17(1):34-45, 2022
L. Coba, R. Confalonieri, M. Zanker, "RecoXplainer: A Library for Development and Offline Evaluation of Explainable Recommender Systems", IEEE Computational Intelligence Magazine, 17(1):46-58, 2022
A. Heuillet, F. Couthouis, N. Díaz-Rodríguez, "Collective eXplainable AI: Explaining Cooperative Strategies and Agent Contribution in Multiagent Reinforcement Learning With Shapley Values", IEEE Computational Intelligence Magazine, 17(1):59-71, 2022
R. Hamon, H. Junklewitz, I. Sanchez, G. Malgieri, P. de Hert, "Bridging the Gap Between AI and Explainability in the GDPR: Towards Trustworthiness-by-Design in Automated Decision-Making", IEEE Computational Intelligence Magazine, 17(1):72-85, 2022

Aims and Scope

Computational Intelligence (CI) encompasses the theory, design, application, and development of biologically and linguistically motivated computational paradigms emphasizing fuzzy systems, neural networks, connectionist systems, genetic algorithms, evolutionary programming, and hybrid intelligent systems in which these paradigms are contained. These techniques and their hybridizations work in a cooperative way, taking profit from the main advantages of each individual technique, in order to solve lots of complex real-world problems for which other techniques are not well suited. CI enables Artificial Intelligence (AI) through simulating natural intelligence in all its forms.

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 AI techniques to automatically extract knowledge from data. Actually, AI is identified as a strategic technology and it is already part of our everyday life. The European Commission states that "EU must therefore ensure that AI is developed and applied in an appropriate framework which promotes innovation and respects the Union's values and fundamental rights as well as ethical principles such as accountability and transparency". It emphasizes the importance of Explainable AI (XAI in short), in order to develop an AI coherent with European values: “to further strengthen trust, people also need to understand how the technology works, hence the importance of research into the explainability of AI systems”. Moreover, as remarked in the XAI 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 require a new generation of XAI systems. They are expected to naturally interact with humans, thus providing comprehensible explanations of decisions automatically made.

XAI is an endeavor to evolve AI methodologies and technology by focusing on the development of agents capable of both generating decisions that a human could understand in a given context, and explicitly explaining such decisions. This way, it is possible to scrutinize the intelligent models and verify if automated decisions are made on the basis of accepted rules and principles, so that decisions can be trusted and their impact justified.

This Special Issue is supported by the IEEE CIS Task Force on Explainable Fuzzy Systems (TF-EXFS). The mission of the TF-EXFS is to lead the development of a new generation of Explainable Fuzzy Systems, with a holistic view of fundamentals and current research trends in the XAI field, paying special attention to fuzzy-grounded knowledge representation and reasoning but also regarding how to enhance human-machine interaction through multi-modal (e.g., graphical or textual modalities) effective explanations.

The scope of this special issue is not limited to the community of researchers in Fuzzy Logic but it is open to contributions by researchers, from both academy and industry, working in the multidisciplinary field of XAI.

Topics

Theoretical Aspects of Explainability, Fairness, Accountability and Transparency
Relations between Explainability and other Quality Criteria (such as Interpretability, Accuracy, Stability, Relevance, etc.)
Dimensions of Interpretability: Readability versus Understandability
Explainability Evaluation and Improvements
Learning Methods and Design Issues for Explainable Systems and Models
Interpretable Machine Learning
Explaining Black-box Models
Hybrid Approaches (e.g., Neuro-Fuzzy Systems) for XAI
Model-specific and Model-agnostic Approaches for XAI
Models for Explainable Recommendations

Explainable Conversational Agents
Self-explanatory Decision-Support Systems
Factual and Counterfactual Explanations
Causal Thinking, Reasoning and Modeling
Cognitive Science and XAI
Argumentation Theory for XAI
Natural Language Technology for XAI
Human-Machine Interaction for XAI
Ethics and Legal Issues for XAI
XAI-based Data Analysis and Bias Mitigation
Safe and Trustworthy AI
Applications of XAI-based Systems
Open Source Software for XAI

Submission

The IEEE Computational Intelligence Magazine (IEEE CIM) publishes peer-reviewed high-quality articles. All manuscripts must be submitted electronically in PDF format. Manuscripts must be in standard IEEE two-column/single space format and adhere to a length of 10-12 pages (including figures and references) for regular papers. A mandatory page charge is imposed on all papers exceeding 12 pages in length.

More information on manuscript details and submission guidelines can be found at the IEEE CIM website.

Important Dates

Paper submission: February 22^nd, 2021
Acceptance/rejection notification: April 22^nd, 2021 (this is a tentative date; each paper is notified as soon as all referees are collected)
Revision due: May 22^nd, 2021 (this is a tentative date; with each notification, in case of accept you will be given revision due date)
Final notification: July 7^st, 2021
Camera-ready due: July 22^nd, 2021 (this date is strict; no delays are admitted)
Publication Date: November 2021

Editors

José M. Alonso (josemaria.alonso.moral@usc.es)

Research Centre in Intelligent Technologies (CiTIUS)

University of Santiago de Compostela (USC)

Campus Vida, E-15782, Santiago de Compostela, Spain

Corrado Mencar (corrado.mencar@uniba.it)

Department of Informatics

University of Bari Aldo Moro, Bari, Italy

Hisao Ishibuchi (hisaoi@cs.osakafu-u.ac.jp)

Department of Computer Science and Engineering

Southern University of Science and Technology, Shenzhen, China

Supported by

Google Sites

Report abuse