Abstract : Work under this grant focused on methods for extracting hidden information from network data, including data from social networks, networks of communications and interactions, heath or disease networks, and brain networks. During the last 12 months of this project, the funding level was cut substantially. Nevertheless, over this period, our team worked on several substantial projects, including the development of several powerful new algorithms for analyzing networks and their application to specific real-world domains. These efforts produced 8 peer-reviewed papers or new preprints, and more than a dozen invited or contributed presentations on these projects. We continued to focus on developing powerful and scalable Bayesian statistical and related inference methods for community structure, hierarchies, core-periphery structure, rankings, and other large-scale network structures, and on discovering the fundamental limits of these techniques for inferring such hidden patterns. Additionally, we focused on algorithms applicable to very large networks, networks with auxiliary information (such as annotations, temporal dynamics, or edge weights), and demonstrations of these techniques to domains of interest.
[1]
Cristopher Moore,et al.
Detectability thresholds and optimal algorithms for community structure in dynamic networks
,
2015,
ArXiv.
[2]
Leto Peel,et al.
Detecting Change Points in the Large-Scale Structure of Evolving Networks
,
2014,
AAAI.
[3]
Aaron Clauset,et al.
Learning Latent Block Structure in Weighted Networks
,
2014,
J. Complex Networks.
[4]
Xiao Zhang,et al.
Identification of core-periphery structure in networks
,
2014,
Physical review. E, Statistical, nonlinear, and soft matter physics.
[5]
Cristopher Moore,et al.
Untangling the roles of parasites in food webs with generative network models
,
2015,
bioRxiv.
[6]
Cristopher Moore,et al.
Phase transitions in semisupervised clustering of sparse networks
,
2014,
Physical review. E, Statistical, nonlinear, and soft matter physics.