Link prediction in multiplex networks based on interlayer similarity

Abstract

Highlights We propose an interlayer similarities measure for multiplex networks. We introduce a link prediction framework based on interlayer similarities for multiplex networks. We examine the impact of interlayer similarities on link prediction in synthetic and real multiplex networks. AbstractSome networked systems can be better modelled by multilayer structure where the individual nodes develop relationships in multiple layers. Multilayer networks with similar nodes across layers are also known as multiplex networks. This manuscript proposes a novel framework for predicting forthcoming or missing links in multiplex networks. The link prediction problem in multiplex networks is how to predict links in one of the layers, taking into account the structural information of other layers. The proposed link prediction framework is based on interlayer similarity and proximity-based features extracted from the layer for which the link prediction is considered. To this end, commonly used proximity-based features such as Adamic-Adar and Jaccard Coefficient are considered. These features that have been originally proposed to predict missing links in monolayer networks, do not require learning, and thus are simple to compute. The proposed method introduces a systematic approach to take into account interlayer similarity for the link prediction purpose. Experimental results on both synthetic and real multiplex networks reveal the effectiveness of the proposed method and show its superior performance than state-of-the-art algorithms proposed for the link prediction problem in multiplex networks.

A Roadmap Toward Predicting Species Interaction Networks (Across Space and Time)

“…However, prima facie, increasing the dimensionality of the object we need to predict (the multiple layers rather than a single network) makes the problem more complicated. Yet, mutli-layer approaches improve prediction in social networks (Jalili et al 2017;Najari et al 2019;Yasami and Safaei 2018), and they may prove useful going forward.…”

Taxonomy of Link Prediction for Social Network Analysis: A Review

“…Then, the dynamic network is a network in which edges may appear and disappear over time and have a temporal character. Lastly, the multilayer network is a network with similar nodes across layers [79].…”

“…Aslan and Kaya [18] also proposed a new link prediction algorithm based on strengthening weighted projection to predict the association between authors and topics and to prevent loss of information in the case if a bipartite network is changed into a unimodal network. In turn, multiplex or multilayer networks have a problem to predict new links at the one layer by using structural information from another layer [79]. Later, Najari et al [79] proposed a novel framework by combining interlayer similarity and proximity-based features, with further extraction of the predicted link from the considered layer.…”

“…In turn, multiplex or multilayer networks have a problem to predict new links at the one layer by using structural information from another layer [79]. Later, Najari et al [79] proposed a novel framework by combining interlayer similarity and proximity-based features, with further extraction of the predicted link from the considered layer.…”

Prediction of new scientific collaborations through multiplex networks

“…Despite its simplicity, this concept has proven to be quite successful for link prediction in scientific collaboration networks [21,22]. Moving from this simple approach, several attempts have been made to improve the prediction of collaborations by incorporating additional layers of data, for instance, by adding information about the organization the authors work at [23], topical interest [24], time at which collaborations are established [25], offline relationships among employees of the same university [26], weights of the collaboration links [27] or journal information [28]. However, in most of these approaches, the scores are computed individually for each set of data and then aggregated into a unique score, possibly after associating a specific weight to each set.…”