Campus Event Calendar
Event Entry
What and Who
Maximum Entropy Approach to Time Aware Link Prediction
Tomasz Tylenda
IMPRS-CS
Master Seminar Talk
IMPRS-CS Master Student
AG 1, AG 2, AG 3, AG 4, AG 5, SWS, RG1, MMCI
Public Audience
English
Note: We use this to send email in the morning.
Date, Time and Location
Monday, 15 December 2008
12:00
60 Minutes
E1 4
024
Saarbrücken
Abstract
Data from many domains can be represented as graphs growing over time.Examples include collaborations among scientists, friendships on social networking websites, etc. A common task is to predict new links based on the current state of the graph. Our main contribution is using temporal information to improve the performance of existing link prediction algorithms. Given a central node and its neighborhood, we build a probabilistic model based on the principle of maximum entropy and use it to rank neighbors according to probability that they we be linked with the central node.
Contact
Stephanie Jörg
0681 93 25 225
--email hidden
passcode not visible
logged in users only
Stephanie Jörg, 12/09/2008 10:53
Stephanie Jörg, 12/09/2008 10:48 -- Created document.
Stephanie Jörg, 12/09/2008 10:48 -- Created document.