Home

                                                              Call for papers
      2018 IJCNN/IEEE World Congress on Computational Intelligence
08-13 July 2018, Windsor Convention Centre, Rio de Janeiro, BRAZIL


Clustering is a well-studied domain. Currently, more and more data are collected from multiple sources or represented by multiple views (e.g., text, video, images, biological data, among others). Also, for the same data there might exist several different structures (clusterings) which are meaningful for the user. In this context, clustering techniques are often required to be able to provide several possibilities for analyzing the data. As a consequence, in recent years, the interdisciplinary research topic on multiple clusterings has drawn significant attention of the data mining community.

Another topic of recent interest in clustering is interactive clustering. For instance, usually clustering is studied in the unsupervised learning framework. However, as pointed out in some studies, in several real-world problems, such as personalized recommendations, it is not possible to reach the “optimal” clustering (the solution that meets the requirements of the user) without interacting with the end user. In order to approach this problem, recently frameworks for interactive clustering with human in the loop have been proposed. These algorithms can interact with the human in steps and receive feedback to improve. 

The aim of this special session is to bring together researchers from Machine Learning and Data Mining which are actively working in the fields of multiple clusterings and interactive clustering. The idea is to cover a wide spectrum of topics, ranging from multi-view clustering, the interaction with human supervisors to constraint-based clustering, and stimulate cross-fertilization. In this context, as it is a cross-disciplinary session, we welcome papers in which techniques such machine learning, neural networks, fuzzy systems and evolutionary computing are used in the context of Interactive/Multiple Clustering.