A Bayesian Model of node interaction in networks
This addresses a limitation in network modeling for researchers in Bayesian statistics and machine learning, but it appears incremental as it builds on existing methods without a major breakthrough.
The paper tackled the problem of modeling link strength in networks based on usage frequency, rather than just predicting link existence, by applying Bayesian priors like the Chinese Restaurant Process and multivariate Gaussian to social network and word co-occurrence datasets.
We are concerned with modeling the strength of links in networks by taking into account how often those links are used. Link usage is a strong indicator of how closely two nodes are related, but existing network models in Bayesian Statistics and Machine Learning are able to predict only wether a link exists at all. As priors for latent attributes of network nodes we explore the Chinese Restaurant Process (CRP) and a multivariate Gaussian with fixed dimensionality. The model is applied to a social network dataset and a word coocurrence dataset.