دانلود A novel time series link prediction method: Learning automata approach

Abstract

Link prediction is a main social network challenge that uses the network structure to predict future links. The common link prediction approaches to predict hidden links use a static graph representation where a snapshot of the  network   is  analyzed  to  find  hidden  or  future  links.  For  example,  similarity  metric  based  link  predictions  are  a common  traditional  approach  that  calculates  the  similarity  metric  for  each  non-connected  link  and  sort  the  links based on their similarity metrics and label the links with higher similarity scores as the future links. Because people activities in social networks are dynamic and uncertainty,  and  the structure of the networks changes over time,  using deterministic graphs for modeling and analysis of the social network may not be appropriate. In the time-series link prediction problem, the time series link occurrences are used to predict the future links. In this paper, we propose a new time series   link  prediction  based  on  learning  automata.  In  the  proposed  algorithm  for  each  link  that  must  be predicted, there  is one learning  automaton and  each  learning  automaton tries to  predict  the  existence  or non-existence of  the  corresponding link. To  predict  the  link  occurrence  in  time  T,  there  is a  chain  consists of  stages  1 throughT-1  and  the  learning  automaton  passes  from these  stages to  learn  the  existence  or non-existence  of  the corresponding  link. Our  preliminary  link  prediction  experiments  with co-authorship  and  email  networks have provided satisfactory results when time series link occurrences are considered.