Backward Direction Link Prediction in Multi-relation Systems
Recently, many researchers have been attracted in link prediction which is an effective technique to be used in graph based models analysis. To the best of our knowledge, most of previous works in this area have not explored the prediction of links in Multi-relation systems and have not explored the prediction of links which could disappear in the future. We argue that these kinds of links are important. At least they can do complement for current link prediction processes in order to plan better for the future. In this paper, we propose a link prediction model, which is capable of predicting backward direction links that might exist and may disappear in the future in Multi-relation systems. Firstly, we present the definition of multi-relation systems and put forward some algorithms which build Multi-relation systems. Then we give backward direction link prediction algorithms in multi-relation systems. At the end, algorithms above are applied in recommendation systems.
KeywordsMulti-relation systems Backward direction link prediction Weight similarity Personalized recommendation
Supported by the Technology Program of Shandong Province under Grant No. 2012GGB01058; Graduate Education Innovative Projects of Shandong Province under Grant No. SDYY10059.
- 1.Getoor L, Diehl CP (2005) Link mining: a survey. J ACM SIGKDD Explor Newslett 7(2):3–12Google Scholar
- 2.Lin W, Chao S (2012) Research on link prediction in no-scale networks. Comput Eng 38(3):67–70Google Scholar
- 3.Allali O, Magnien C, Latapy M (2011) Link prediction in bipartite graphs using internal links and weighted projection. In: IEEE conference on computer communications workshops, pp 936–941Google Scholar