A novel cross-network node pair embedding methodology for anchor link prediction

Anchor link prediction across social networks is highly important for multiple social network analysis. Traditional methods rely heavily on user-generated information or the quality of network topology information and are not suitable for real-life multiple social networks. Deep learning methods based on graph embedding are limited by the latent similarity of the associated nodes in a single network and the overlap between different networks used for projections of multiple network feature spaces. In this paper, we propose a novel method which eliminates overlapping restriction. The proposed method consists of two phases. First, graph embedding with reconciliation of similarity and distinction is used to obtain an effective embedding vector space. Second, cross-network features for supervised learning are constructed via cross-network feature mining based on collisions between the features of nodes belonging to different networks. The combination of similarity reduction and cross-network feature collisions alleviates the restriction on overlapping parts. Extensive experiments on large-scale real-life social networks demonstrate that the proposed method significantly outperforms the state-of-the-art methods in terms of both precision and robustness.

Automated summary

This paper proposes a novel method for anchor link prediction across different social networks. The method utilizes graph embedding and cross-network feature mining to construct an effective feature space, overcoming the limitations of traditional methods in real-life applications.