报告题目：Designing and Interpreting Rule-Based Architectures Under Privacy Constraints: A Framework of Granular Computing
报告人: Witold Pedrycz 加拿大皇家科学院院士
Witold Pedrycz is Professor and Canada Research Chair (CRC) in Computational Intelligence in the Department of Electrical and Computer Engineering, University of Alberta, Edmonton, Canada. He is also with the Systems Research Institute of the Polish Academy of Sciences, Warsaw, Poland. He is a foreign member of the Polish Academy of Sciences, and a Fellow of the Royal Society of Canada, IEEE, and IFSA. He is a recipient of numerous awards including a prestigious Norbert Wiener award from the IEEE Systems, Man, and Cybernetics Society, IEEE Canada Computer Engineering Medal, Cajastur Prize for Soft Computing, Killam Prize, and a Fuzzy Pioneer Award from the IEEE Computational Intelligence Society.
His main research directions involve Computational Intelligence, fuzzy modeling and Granular Computing, knowledge discovery and data mining, fuzzy control, pattern recognition, knowledge-based neural networks, relational computing, and Software Engineering. He is an author of 15 research monographs covering various aspects of Computational Intelligence, data mining, and Software Engineering.
Dr. Pedrycz is intensively involved in editorial activities. He is an Editor-in-Chief of Information Sciences and Editor-in-Chief of WIREs Data Mining and Knowledge Discovery (Wiley). He currently serves as an Associate Editor of IEEE Transactions on Fuzzy Systems and is a member of a number of editorial boards of other international journals.
In data analytics, system modeling, and decision-making models, the aspects of interpretability and explainability are of paramount relevance as emphasized in numerous studies on explainable Artificial Intelligence (XAI). Those requirements are especially timely when the design of models has to be realized when considering strict requirements of privacy and security.
We advocate that to efficiently address these challenges, it becomes beneficial to engage the fundamental framework of Granular Computing. It is demonstrated that a conceptualization of information granules can be conveniently carried out with the use of information granules (for example, fuzzy sets, sets, rough sets, and alike).
A systematic way of enhancing interpretability of functional rule-based models with the rules in the form “if x is A then y =f(x)” is discussed. The interpretability mechanisms are focused on the elevation of interpretability of the conditions and conclusions of the rules. It is shown that augmenting interpretability of conditions is achieved by (i) decomposing a multivariable information granule into its one-dimensional components, (ii) their symbolic characterization, and (iii) linguistic approximation. A hierarchy of interpretation mechanisms is systematically established. We also discuss how this increased interpretability associates with the reduced accuracy of the rules and how sound trade-offs between these features are formed.
We cover a comprehensive discussion of information granules-oriented design of rule-based architectures. A way of forming condition parts of the rules through unsupervised federated learning is discussed along with algorithmic developments. Strategies of joint and separate learning of condition parts and conclusion parts are outlined. A granular characterization of the model formed by the server vis-a-vis data located at individual clients is presented. It is demonstrated that the quality of the rules at the client’s end is described in terms of granular parameters and subsequently the global model becomes represented as a granular model with parameters in the form of information granules of type-2.