Overlapping Communities and Roles in Networks with Node Attributes: Probabilistic Graphical Modeling, Bayesian Formulation and Variational Inference

This paper interrogates the history of same-sex dancing among women in Buenos Aires' tango scene, focusing on its increasing visibility since 2005. Two overlapping communities of women are invoked. Queer tangueras are queer-identified female tango dancers and their allies who dance tango in a way that attempts to de-link tango's two roles from gender. Rebellious wallflowers are women who practice, teach, perform, and dance with other women in predominantly straight environments. It is argued that the growing acceptance of same-sex dancing in Argentina is due to the confluence of four developments: 1) the rise of tango commerce, 2) innovations of tango nuevo, 3) changing laws and social norms around lesbian, gay, bisexual, and transgender rights, and 4) synergy between queer tango dancers and heterosexual women who are frustrated by the limits of tango's gender matrix. The author advocates for increased alliances between rebellious wallflowers and queer tangueras, who are often segregated from each other in Buenos Aires' commercial tango industry.

Download Full-text

Faculty Opinions recommendation of Graphical modeling of the joint distribution of alleles at associated loci.

Faculty Opinions – Post-Publication Peer Review of the Biomedical Literature ◽

10.3410/f.1021516.245647 ◽

2004 ◽

Author(s):

Daniel Weeks

Keyword(s):

Joint Distribution ◽

Graphical Modeling

Download Full-text

Detecting Overlapping Communities with Heuristic Expansion Method Based on Rough Neighborhood

Chinese Journal of Computers ◽

10.3724/sp.j.1016.2013.02078 ◽

2014 ◽

Vol 36 (10) ◽

pp. 2078-2086 ◽

Cited By ~ 5

Author(s):

Ze-Hua ZHANG ◽

Duo-Qian MIAO ◽

Jin QIAN

Keyword(s):

Expansion Method ◽

Overlapping Communities

Download Full-text

Crimea and the South China Sea

10.1093/oso/9780190697570.003.0006 ◽

2018 ◽

Cited By ~ 1

Author(s):

Anthea Roberts

Keyword(s):

South China Sea ◽

Case Studies ◽

South China ◽

The South China Sea ◽

Invisible College ◽

The South ◽

Overlapping Communities ◽

China Sea ◽

High Profile ◽

Spheres Of Influence

Although we often hear reference to the “invisible college” of international lawyers, it may be better to understand international lawyers as constituting a “divisible college” whose members hail from different states and regions and often form distinct, though sometimes overlapping, communities with their own understandings and approaches, as well as their own influences and spheres of influence. This chapter draws on two recent high-profile controversies—Crimea’s annexation by, or reunification with, Russia in 2014, and the legality and legitimacy of the award in the South China Sea arbitration in 2016—to explore how the divisible college of international lawyers operates with respect to Chinese, Russian, and Western international lawyers. It looks at the extent to which international lawyers in these case studies operated in their own silos or made an effort to communicate across national and geopolitical divides.

Download Full-text

SAR Target Recognition via Meta-Learning and Amortized Variational Inference

Sensors ◽

10.3390/s20205966 ◽

2020 ◽

Vol 20 (20) ◽

pp. 5966

Author(s):

Ke Wang ◽

Gong Zhang

Keyword(s):

Target Recognition ◽

Probability Distributions ◽

Automatic Target Recognition ◽

Variational Inference ◽

Training Data ◽

Superior Performance ◽

Small Data ◽

Meta Learning ◽

Radar Automatic Target Recognition ◽

Global Parameters

The challenge of small data has emerged in synthetic aperture radar automatic target recognition (SAR-ATR) problems. Most SAR-ATR methods are data-driven and require a lot of training data that are expensive to collect. To address this challenge, we propose a recognition model that incorporates meta-learning and amortized variational inference (AVI). Specifically, the model consists of global parameters and task-specific parameters. The global parameters, trained by meta-learning, construct a common feature extractor shared between all recognition tasks. The task-specific parameters, modeled by probability distributions, can adapt to new tasks with a small amount of training data. To reduce the computation and storage cost, the task-specific parameters are inferred by AVI implemented with set-to-set functions. Extensive experiments were conducted on a real SAR dataset to evaluate the effectiveness of the model. The results of the proposed approach compared with those of the latest SAR-ATR methods show the superior performance of our model, especially on recognition tasks with limited data.

Download Full-text