Mixed Membership Relational Clustering

 Background: 

Recently, semi-supervised clustering has attracted significant attention, which is a special type of clustering using both labeled and unlabeled data. It can be formulated as clustering on single-type relational data consisting of attributes and homogeneous relations. This invention is based on a novel probabilistic model for relational clustering, which also provides a principal framework to unify various important clustering tasks including traditional attributes-based clustering, semi-supervised clustering, co-clustering and graph clustering.

 Technology Overview: 

This model seeks to identify cluster structures for each type of data objects and interaction patterns between different types of objects. It is applicable to relational data of various structures. Under this model, we propose parametric hard and soft relational clustering algorithms under a large number of exponential family distributions.

 Advantages: 

• The invention is applicable to various relational data from various applications.
• It is capable of adapting different distribution assumptions for different relational data with different statistical properties.
• The resulting parameter matrices provides a intuitive summary for the hidden structure for the relational data.

 Intellectual Property Summary: 

• U.S. 8,285,719
• U.S. 8,676,805
• U.S. 8,996,528
• U.S. 9,372,915

Patent rights available for licensing.