Leveraging Node Attributes for Link Prediction via Meta-path Based Proximity

Link prediction is an important task of graph data mining that facilitates a series of applications including recommendation system, network reconstruction, etc. Node attributes make it possible to predict potential links between isolate or unobserved nodes. That attracts more and more attention of academia and industry on leveraging node attributes for link prediction. Numerous link prediction methods are based on attributed network embedding, but they are not specially designed for link prediction and may suffer potential loss of accuracy due to reduction of dimension. In this paper, we propose a direct and efficient way to utilize path-based proximity for link prediction. In many works in the past, node attributes were regarded as a different property of networks compared to heterogeneity. This paper creatively treats attributes as a distinct type of nodes and extends attributed networks to heterogeneous networks. It proposes a framework based on transition probability of meta-path guided random walks to get attributes and structure incorporated proximity of nodes. Link prediction experiments on six real-world datasets were conducted by three types of baselines methods. The experimental results demonstrates that the proposed method has exceptional performance in terms of both robustness and accuracy on most datasets.