Many real-world networks exhibit hierarchical organization. Previous models of hierarchies within relational data has focused on binary trees; however, for many networks it is unknown whether there is hierarchical structure, and if there is, a binary tree might not account well for it. We propose a generative Bayesian model that is able to infer whether hierarchies are present or not from a hypothesis space encompassing all types of hierarchical tree structures. For efficient inference we propose a collapsed Gibbs sampling procedure that jointly infers a partition and its hierarchical structure. On synthetic and real data we demonstrate that our model can detect hierarchical structure leading to better link-prediction than competing models. Our model can be used to detect if a network exhibits hierarchical structure, thereby leading to a better comprehension and statistical account the network.
|Title of host publication||2012 3rd International Workshop on Cognitive Information Processing (CIP)|
|Number of pages||6|
|Publication status||Published - 2012|
|Event||3rd International Workshop on Cognitive Information Processing (CIP) - Baiona, Spain|
Duration: 28 May 2012 → 30 May 2012
|Workshop||3rd International Workshop on Cognitive Information Processing (CIP)|
|Period||28/05/2012 → 30/05/2012|