Learning to Generate Networks
Machine Learning
2014-11-11 v2 Social and Information Networks
Physics and Society
Abstract
We investigate the problem of learning to generate complex networks from data. Specifically, we consider whether deep belief networks, dependency networks, and members of the exponential random graph family can learn to generate networks whose complex behavior is consistent with a set of input examples. We find that the deep model is able to capture the complex behavior of small networks, but that no model is able capture this behavior for networks with more than a handful of nodes.
Cite
@article{arxiv.1405.5868,
title = {Learning to Generate Networks},
author = {James Atwood and Don Towsley and Krista Gile and David Jensen},
journal= {arXiv preprint arXiv:1405.5868},
year = {2014}
}
Comments
Neural Information Processing Systems 2014 Workshop on Networks: From Graphs to Rich Data