Core of communities in bipartite networks

Abstract

We use the information present in a bipartite network to detect cores of communities of each set of the bipartite system. Cores of communities are found by investigating statistically validated projected networks obtained using information present in the bipartite network. Cores of communities are highly informative and robust with respect to the presence of errors or missing entries in the bipartite network. We assess the statistical robustness of cores by investigating an artificial benchmark network, the co-authorship network, and the actor-movie network. The accuracy and precision of the partition obtained with respect to the reference partition are measured in terms of the adjusted Rand index and of the adjusted Wallace index respectively. The detection of cores is highly precise although the accuracy of the methodology can be limited in some cases.

Reconstructing irreducible links in temporal networks: which tool to choose depends on the network size

“…Backbone network In the ETFM the link is significant if its weight, w ts ij , is above the threshold w ts ij (β ) (top), according to equation (8). In the TDF the link is significant if the observed normalized weight, r ts ij , is above the threshold r ts ij (β ) (bottom), and according to equation (13). As a result, the backbone networks are extracted from the temporal network (right graphics).…”

“…In all of the three approaches under consideration, a statistical test is carried out for all the N E links observed at least once in the evolving network. The EADM and ETFM use equation (8), while the TDF employs equation (13). Since multiple hypotheses are tested, a multiple hypothesis test correction is required [36].…”

Bootstrap validation of links of a minimum spanning tree

“…Ref. [15] has generalized the Wallace index to obtain an adjusted index varying between −∞ and one. It assumes a zero value when the test partition is included into the reference partition not better than in a random case.…”

Complex network models, graph mining and information extraction from real-world systems

“…Then, we discussed how a generalized version of PageRank and HITS algorithms could be dened for bipartite networks and, in a case study, we applied it on wine tasting datasets in order to rank tasters based on their ability and professional skills. The results were published in a journal [21] and appeared in conference proceeding [122]. The following paragraphs briey summarize the main results of the chapter.…”

“…Ezután a PageRank és HITS algoritmusok egy általánosítását tárgyaltuk, majd bemutattuk egy lehetséges új alkalmazását borkóstolási adatokra. Az eredmények egy nemzetközi folyóiratban [21] kerülnek publikálására, illetve egy nemzetközi konferencia kiadványban [122] jelentek meg. A következ® pontokban összegezzük a fejezet f® eredményeit.…”