The Impact of Partial Information on Network Inference and Characterization

• Activity Number: 524
• Type: Contributed
• Date/Time: Wednesday, August 4, 2010 : 10:30 AM to 12:20 PM
• Sponsor: Section on Statistical Learning and Data Mining
• Author(s): Natallia V. Katenka*+ and Eric Kolaczyk
• Companies: Boston University and Boston University
• Keywords: Association networks ; canonical correlation ; gene/protein networks

Abstract

Association networks represent systems of interacting elements, where a link between two different elements indicates a sufficient level of similarity between element attributes. We study the impact of partial information on network inference and characterization, when only a subset of attributes is available. Quantifying similarity between nodes using canonical correlation, we examine both theoretically and numerically the implications of the choice and number of node attributes on the ability to detect network links and, more generally, to estimate higher-level network summary statistics, such as node degree, clustering coefficients, and measures of centrality. We consider in detail the case of two attributes and discuss generalization of our findings to more than two attributes. Our work is motivated and illustrated in the context of gene/protein regulatory networks in human cancer.