Network Classification with Incomplete Information
Loading...
Authors
Yoshida, Ruriko
Vu, Carolyne
Spinelli, Ross
Subjects
machine learning
network classifications
network completion problem
random forests
network classifications
network completion problem
random forests
Advisors
Date of Issue
2020-03
Date
Period of Performance: 03/15/2019–03/30/2020
Publisher
Monterey, California. Naval Postgraduate School
Language
Abstract
With the growth of accessible data, particularly for incomplete networks, a demand for effective methods of analyzing networks has emerged. Even as means for data collection advance, incomplete information remains a reality for numerous reasons. For example, data can be obscured by excessive noise, and surveys for information typically contain some non- respondents. In other cases, simple inaccessibility restricts observation. Also, for illicit groups, we are confronted with attempts to conceal important elements or propagation of false information. In the real-world, it is difficult to determine when the observed network is both accurate and complete. In this research, we consider two objectives: (1) a method for classification of incomplete networks (network classification) and (2) inference on how much missing information (network completion problem). In contrast to the current method of training models with only complete information, we examine the effects of training our classification model, and training network completion problem, with both complete and incomplete network information. Our results strongly indicate the need to include incomplete network representations in training the classification model and network completion. Incorporating incomplete networks at various stages of completeness allow the machine to examine and learn the nuances of incomplete networks. By allowing the machine to study incomplete network structural features, it has an improved ability to recognize and classify other incomplete networks. We also confirm these simple, easily calculated network features are sufficient to classify an incomplete network and network completion.
Type
Report
Description
NPS NRP Executive Summary
Series/Report No
Department
Operations Research (OR)
Organization
Naval Research Program
Identifiers
NPS Report Number
NPS-19-N072-A
Sponsors
Naval Research Program
Topic Sponsor: N41L
Research POC Name: Eric Bach, CAPT, USN
Topic Sponsor: N41L
Research POC Name: Eric Bach, CAPT, USN
Funder
Format
5 p.
Citation
Distribution Statement
Rights
This publication is a work of the U.S. Government as defined in Title 17, United States Code, Section 101. Copyright protection is not available for this work in the United States.