Implicit consensus clustering from multiple graphs

Abstract Dealing with relational learning generally relies on tools modeling data. An undirected graph can represent these data vertices depicting entities and edges describing the relationships between entities. These be well represented by multiple graphs over same set of arising from different catching heterogeneous relations. The those networks are often structured in unknown clusters varying properties connectivity. as a three-way tensor, where each slice tensor depicts which is count matrix. To extract relevant clusters, we propose an appropriate model-based co-clustering capable dealing graphs. proposed model seen suitable extension mixture models graphs, while obtained treated consensus clustering nodes Applications real datasets comparisons multi-view decomposition methods show interest our contribution.