Embedded Files
Special Session
IEEE World Congress on Computational Intelligence WCCI 2024
Aim and Scope
Aim and Scope
In an era of data-driven insights, a fundamental challenge lies in designing and building Computational Intelligence (CI) systems from decentralized data while respecting the growing requirements for trustworthiness.
Among the paradigms for collaborative learning of CI models, Federated Learning (FL) has recently been proposed to cope with the data privacy issue, allowing different parties to collaborate in the training of a CI model without necessarily sharing their own data. Another crucial aspect of trustworthiness is explainability, typically achieved either through the design of inherently interpretable models or through the adoption of post-hoc techniques.
The aim of this session is to provide an international and multidisciplinary forum for discussing techniques for collaborative learning of trustworthy CI systems, with a special focus on Fuzzy and Neuro-Fuzzy Systems.
While the relationship between fuzzy systems and explainability is widely acknowledged, a topical challenge is to develop techniques for learning fuzzy and neuro-fuzzy systems in a privacy-preserving manner. Likewise, concepts from fuzzy set theory can be exploited to enhance algorithms for collaborative learning.
Neural Networks are among the most widely investigated CI techniques in the framework of FL and collaborative learning in general. However, they are often regarded as black box models and the requirement of explainability is neglected
This special session is supported by the IEEE-CIS Task Force on Explainable Fuzzy Systems.
Topics of Interest
Topics of Interest
The topics of interest include (but are not limited to):
Trustworthy Collaborative Artificial Intelligence
Collaborative/Federated Learning of Explainable Artificial Intelligence Models
Collaborative/Federated Learning of Interpretable by-design models
Collaborative/Federated Learning and post-hoc explainability techniques
Collaborative/Federated Supervised and Unsupervised Learning for Fuzzy Models
Fuzzy set theory for Collaborative/Federated Learning
Privacy Preserving Machine Learning
Applications of Trustworthy Collaborative Artificial Intelligence
Submission and publication info
Submission and publication info
Paper Submission Deadline: January 15, 2024 EXTENDED January 29, 2024
Please submit your paper directly through the IEEE-WCCI 2024 submission website selecting this special session as main research topic.
Main Topic: "SS: Collaborative Learning of Trustworthy Computational Intelligence Systems"
Submitted papers will be peer-reviewed with the same criteria of other FUZZ-IEEE tracks.
The papers accepted for the special session will be included in the FUZZIEEE 2024 proceedings and will be published by the IEEE Xplore Digital Library.
Committee
Committee
Organizing Committee
Pietro Ducange, University of Pisa, Italy
Francesco Marcelloni, University of Pisa, Italy
Witold Pedrycz, University of Alberta, Canada
Alessandro Renda, University of Pisa, Italy
Publicity and Communication Chair:
José Luis Corcuera Bárcena, University of Pisa, Italy
Report abuse