Supervised Learning for Link Prediction Using Similarity Indices

P. 1–8.

Korolev S., Жуков Л. Е.

The problem of link prediction gathered a lot of attention in the last few years, arising in dierent applications ranging from recommendation systems to social networks. In this paper, we will describe the most popular similarity indices, compare their performance in their ability to show links with the highest probability of being removed from initial network and describe the approach that allows to use them to predict missing links using supervised machine learning. We will show the accuracy of prediction of this method on examples of real networks.
 

Ключевые слова: анализ сетей, теория графов, network analysis, link prediction, graph theory

В книге

"Информационные технологии и системы 2015" 39-я междисциплинарная школа-конференция 7 – 11 сентября, Олимпийская деревня, Сочи, Россия

St. Petersburg: Институт проблем передачи информации им. А.А. Харкевича РАН, 2015.