Detecting Communities in K-Partite K-Uniform (Hyper)Networks

Abstract

In social tagging systems such as Delicious and Flickr, users collaboratively manage tags to annotate resources. Naturally, a social tagging system can be modeled as a (user, tag, resource) hypernetwork, where there are three different types of nodes, namely users, resources and tags, and each hyperedge has three end nodes, connecting a user, a resource and a tag that the user employs to annotate the resource. Then how can we automatically cluster related users, resources and tags, respectively? This is a problem of community detection in a 3-partite, 3-uniform hypernetwork. More generally, given a K-partite K-uniform (hyper)network, where each (hyper)edge is a K-tuple composed of nodes of K different types, how can we automatically detect communities for nodes of different types? In this paper, by turning this problem into a problem of finding an efficient compression of the (hyper)network's structure, we propose a quality function for measuring the goodness of partitions of a K-partite K-uniform (hyper)network into communities, and develop a fast community detection method based on optimization. Our method overcomes the limitations of state of the art techniques and has several desired properties such as comprehensive, parameter-free, and scalable. We compare our method with existing methods in both synthetic and real-world datasets.

User ratings analysis in social networks through a hypernetwork method

“…The tripartite hypergraph model was extended by defining additional quantities and empirically measuring these quantities for two real-world folksonomies , while a supernetwork model of internet public opinion has been used to examine the functions of indexes such as node superdegree, superedge-superedge distance, and superedge overlap . A framework for clustering and community detection in some systems using hypergraph representations has also been proposed (Michoel & Nachtergaele, 2012), as well as an algorithm based on a quality function for measuring the goodness of different partitions of a tripartite hypergraph into communities (Liu & Murata, 2011) and the 8 chaotic synchronization of hypergraphs (Krawiecki, 2014). Another new concept related to hypernetworks, a hyperstructure, has been proposed and its efficiency defined (Criado et al, 2010).…”

A Framework for Community Detection in Heterogeneous Multi-Relational Networks

“…Barber proposed a bipartite modularity which assumes a bipartite structure of the null model, and devised a label propagation algorithm called BRIM [2] for optimization. Murata proposed a k-partite modularity in a unified way as the definition of modularity, in the sense that his k-partite modularity can reduce to modularity if the k-partite network becomes a unipartite network [34,33] [47] and k-partite networks [27]. Moreover, there are methods for simultaneously clustering related sets of heterogeneous data, such as documents and words.…”

Detecting profilable and overlapping communities with user-generated multimedia contents in LBSNs

“…For example, in social tagging systems, users collaboratively manage tags to annotate resources and the tagging relationship involves three different entities: users, resources and tags. These kinds of multimodality network need a very different treatment for community detection tasks [Murata and Ikeya 2010;Liu and Murata 2011] (Figure 2(c)). Liu and Murata [2011] proposed a structural information compression approach to detect communities in a general k-partite k-uniform hypernetwork.…”

“…These kinds of multimodality network need a very different treatment for community detection tasks [Murata and Ikeya 2010;Liu and Murata 2011] (Figure 2(c)). Liu and Murata [2011] proposed a structural information compression approach to detect communities in a general k-partite k-uniform hypernetwork. In this article, we go one step further by considering community detection in a k-partite nonuniform hypernetwork, where each hyperedge may involve different number of vertices from the same/different modalities ( Figure 2(d)).…”