Differential evolution of correlation indexes for link prediction

Determining the appropriate binary correlation indexes is a central issue for neighbourhood-based Link Prediction techniques. In those approaches correlation-based similarity measures, evaluated on the neighbourhood of a given pair of nodes in a training network, are used to assess the likelihood of those nodes developing new links in the future. It has been observed that, although some similarity measures generally perform better than others, no single binary correlation is optimal for all domains. In this work we introduce a technique which evolves a population of correlation indexes, using a Differential Evolution (DE) algorithm, in order to determine the binary correlation index having the best prediction performance with respect to specific network domains. DE evolves the parameters of meta-indexes, structures which describe and extend classes of known binary similarity indexes. Preliminary experiments show that the proposed correlation indexes evolution method has performances equivalent and in some cases improving the best correlation indexes known for each tested domain, while it provides the remarkable advantage of domain self-adaptability.