Three-Mode Fuzzy Co-Clustering Based on Probabilistic Concept and Comparison with FCM-Type Algorithms
Katsuhiro Honda, Issei Hayashi, Seiki Ubukata, Akira Notsu · Journal of Advanced Computational Intelligence and Intelligent Informatics · 2021
Three-mode fuzzy co-clustering is a promising technique for analyzing relational co-occurrence information among three mode elements. The conventional FCM-type algorithms achieved simultaneous fuzzy partition of three mode elements based on the fuzzyc-means (FCM) concept, and then, they often suffer from careful tuning of three independent fuzzification parameters. In this paper, a novel three-mode fuzzy co-clustering algorithm is proposed by modifying the conventional aggregation criterion of three elements based on a probabilistic concept. The fuzziness degree of three-mode partition can be easily tuned only with a single parameter under the guideline of the probabilistic standard. The characteristic features of the proposed method are compared with the conventional algorithms through numerical experiments using an artificial dataset and are demonstrated in application to a real world dataset of MovieLens movie evaluation data.