Solving link-oriented tasks in signed network via an embedding approach

In this paper, we study the link-oriented tasks in signed network, i.e., labeling link signs and predicting new links. Usually, prior arts directly focus on the link signs, while their intrinsic structural regularities have been largely ignored. Furthermore, these techniques suffer the sensitiveness to the high dimension and sparsity of networks. To deal with these tasks, with verifying the effect of second-order distance in signed network, we propose a novel Link-oriented Signed Network Embedding (LSNE) model, in which network embedding technique is adapted to capture both first-order and second-order distance. Along this line, the link-oriented tasks will be intuitively solved. Extensive experiments on two real-world datasets demonstrate that LSNE could significantly outperform the comparison approaches.