Grid-Based Fuzzy Processing for Parallel Learning the Document Similarities

Document co-clustering methods allow to efficiently capture high-order similarities between objects described by rows and columns of a data matrix. In Alouane et al. (2013), a method for simultaneous computation of similarity matrices between objects (documents or sentences) and between descriptors (sentences or words), each one being built on the other one, according to a fuzzy triadic model based on the three-partite graph. Because of the development of the Web and the high availability of storage spaces, documents become more accessible. This makes the fuzzy computing very expensive. In the present case, the development of fuzzification algorithms of fuzzification requires the integration of a deployment platform with the required processing power. The choice of a grid architecture seems to be an appropriate answer to our needs since it allows us to distribute the processing over all the machines of the platform, thus creating the illusion of a virtual computer able to solve important computing problems which require very long run times in a single machine environment. The authors propose to enhance similarity by upstream and downstream parallel processing. The first deploys the fuzzy linear model in a Grid environment. The second deals with multi-view datasets while introducing different architectures by using several instances of a fuzzy triadic similarity algorithm.