Topological link prediction is the task of assessing the likelihood of new future links based ontopological properties of entities in a network at a given time. In this paper, we introduce amultistrain bacterial di®usion model for link prediction, where the ranking of candidate links isbased on the mutual transfer of bacteria strains via physical social contact. The model incorporatesparameters like e±ciency of the receiver surface, reproduction rate and number of socialcontacts. The basic idea is that entities continuously infect their neighborhood with their ownbacteria strains, and such infections are iteratively propagated on the social network over time.The probability of transmission can be evaluated in terms of strains, reproduction, previoustransfer, surface transfer e±ciency, number of direct social contacts i.e. neighbors, multiplepaths between entities. The value of the mutual strains of infection between a pair of entitiesis used to rank the potential arcs joining the entity nodes. The proposed multistrain di®usionmodel and mutual-strain infection ranking technique have been implemented and testedon widely accepted social network data sets. Experiments show that the MSDM-LP andmutual-strain di®usion ranking technique outperforms state-of-the-art algorithms for neighborbasedranking.
A Multistrain Bacterial Diffusion Model for Link Prediction
Milani, Alfredo
2017-01-01
Abstract
Topological link prediction is the task of assessing the likelihood of new future links based ontopological properties of entities in a network at a given time. In this paper, we introduce amultistrain bacterial di®usion model for link prediction, where the ranking of candidate links isbased on the mutual transfer of bacteria strains via physical social contact. The model incorporatesparameters like e±ciency of the receiver surface, reproduction rate and number of socialcontacts. The basic idea is that entities continuously infect their neighborhood with their ownbacteria strains, and such infections are iteratively propagated on the social network over time.The probability of transmission can be evaluated in terms of strains, reproduction, previoustransfer, surface transfer e±ciency, number of direct social contacts i.e. neighbors, multiplepaths between entities. The value of the mutual strains of infection between a pair of entitiesis used to rank the potential arcs joining the entity nodes. The proposed multistrain di®usionmodel and mutual-strain infection ranking technique have been implemented and testedon widely accepted social network data sets. Experiments show that the MSDM-LP andmutual-strain di®usion ranking technique outperforms state-of-the-art algorithms for neighborbasedranking.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
