Abstract
Link inference, i.e., inferring links between vertices in a heterogeneous information network with heterogeneous vertices and edges, has been extensively studied in recent years. So far, many machine learning-based methods have been proposed for link inference, which can be classified into two categories, namely, supervised and unsupervised. Supervised methods perform well but highly rely on feature selection and training data. Although unsupervised methods are inferior to supervised ones, they work in a relatively simple way without considering the class distribution of the training data. In this paper, we investigate the link inference problem in heterogeneous information networks by proposing a knapsack-constrained inference method. Specifically, we integrate dynamic information into the heterogeneous information network and further formalize the link inference problem as a knapsack-like problem. We then solve it by the virtue of a 0-1 knapsack analogous optimization approach and investigate the time complexity of the proposed approach. Finally, experimental results show that the proposed unsupervised method can obtain high performance comparable to supervised method for some cases.
Funding Information
  • National Key Research and Development Program of China (2016YFB1000902)
  • National Grand Fundamental Research 973 Program of China (2012CB316303, 2014CB340401)
  • National Natural Science Foundation of China (61402442, 61572469, 91646120, 61572473, 61303244, 61402124)

This publication has 31 references indexed in Scilit: