Dynamic Social Network Analysis using Latent Space Models

From Cohen Courses
Revision as of 17:02, 1 April 2011 by Ssomanch (talk | contribs)
Jump to navigationJump to search

This is one of the paper written in course Social Media Analysis 10-802 in Spring 2011

Citation

Purnamrita Sarkar, Andrew W. Moore "Dynamic Social Network Analysis using Latent Space Models"

Online Version

SIGKDD 2005

Summary

This paper address the problem of Social Network Analysis using the method of Latent Space Models. More specifically, it addresses the problem of network evolution in social network analysis, by modelling the way in which the friendships drift over time. It efficiently learns this even when n is large, by assuming that nodes represented by points in the latent space do not make large movements over time. Hence it is a latent space model developed for dynamic analysis of social networks to predict the future link structure of the graph.

This paper is generalization of static modelling in Latent Space Models to Dynamic Social Networks by allowing latent coordinates to change smoothly over time, that is, between any two discretized time steps large movements of points are improbable.

This technique is applied to NIPS data to analysis the dynamics of network evolution.

Overview of the Method

Suppose that each observed link is associated with a discrete time step, then each time step produces its own graph. Further, with the Markov assumption the latent locations at the next time step are conditionally independent of locations in all other time steps given locations in current time step. This is very similar to method to HMM models.

Let be the graph at the time step t with n nodes. Let each node at the time step t be represented in p-dimensional latent space, and let be a Failed to parse (unknown function "\x"): {\displaystyle n\x\p} matrix where each row represents the co-ordinates of a node. The conditional independence assumption shown in the figure below and hence we have the following

Failed to parse (unknown function "\argmax"): {\displaystyle \begin{array}{lcl} X_t & = & \argmax_X P(X\|\G_t, X_{t-1})\\ & = & \argmax_X P(G_t | X) P(X|X_{t-1})\\ \end{array} }


Learning Stage One: Linear Approximation

Learning Stage Two: Non linear search

Datasets Used

Experimental Results

Conclusion