Learning Representations in Directed Networks

Bartunov S., Ivanov O.

We propose a probabilistic model for learning continuous vector representations of nodes in directed networks. These representations could be used as high quality features describing nodes in a graph and implicitly encoding global network structure. The usefulness of the representations is demonstrated on link prediction and graph visualization tasks. Using representations learned by our method allows to obtain results comparable to state of the art methods on link prediction while requires much less computational resources. We develop an efficient online learning algorithm which makes it possible to learn representations from large and non-stationary graphs. It takes less than a day on a commodity computer to learn high quality vectors on LiveJournal friendship graph consisting of 4.8 million nodes and 68 million links and the reasonable quality of representations can be obtained much faster.

Keywords: машинное обучение, machine learning, Graph Mining, анализ графов, Representation learning, обучение представлений

In book

Analysis of Images, Social Networks and Texts. 4th International Conference, AIST 2015, Yekaterinburg, Russia, April 9–11, 2015, Revised Selected Papers

Vol. 542: Series: Communications in Computer and Information Science. , Switzerland: Springer, 2015.