Affiliation:
1. Department of Mathematics and Statistics, Wake Forest University, Winston-Salem, NC 27109
2. Department of Physics, Wake Forest University, Winston-Salem, NC 27109
Abstract
Significance
Community structure arising through relationships and interactions is essential to our understanding of the world around us. Leveraging social concepts of conflict and support, we introduce a method to transform input dissimilarity comparisons into output pairwise relationship strengths (or
cohesion
) and resulting weighted networks. The introduced perspective may be particularly valuable for data with varying local density such as that arising from complex evolutionary processes. Mathematical results, together with applications in linguistics, genetics, and cultural psychology as well as to benchmark data, have been included. Together, these demonstrate how meaningful community structure can be identified without additional inputs (e.g., number of clusters or neighborhood size), optimization criteria, iterative procedures, or distributional assumptions.
Publisher
Proceedings of the National Academy of Sciences
Reference54 articles.
1. R. Chiong, Nature-Inspired Algorithms for Optimisation (Springer, 2008), vol. 193.
2. Algorithms Inspired in Social Phenomena
3. Latent Space Approaches to Social Network Analysis
4. General notions of statistical depth function;Zuo Y.;Ann. Stat.,2000
5. Lens depth function and k-relative neighborhood graph: Versatile tools for ordinal data analysis;Kleindessner M.;J. Mach. Learn. Res.,2017
Cited by
6 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献