More Like this

1. The duality of networks and groups: Models to generate two-mode networks from one-mode networks

   https://doi.org/10.1017/nws.2023.3  

   Neal, Zachary P. ( January 2023 , Network Science)

   Abstract Shared memberships, social statuses, beliefs, and places can facilitate the formation of social ties. Two-mode projections provide a method for transforming two-mode data on individuals’ memberships in such groups into a one-mode network of their possible social ties. In this paper, I explore the opposite process: how social ties can facilitate the formation of groups, and how a two-mode network can be generated from a one-mode network. Drawing on theories of team formation, club joining, and organization recruitment, I propose three models that describe how such groups might emerge from the relationships in a social network. I show that these models can be used to generate two-mode networks that have characteristics commonly observed in empirical two-mode social networks and that they encode features of the one-mode networks from which they were generated. I conclude by discussing these models’ limitations and future directions for theory and methods concerning group formation. 

   more » « less
2. Does gender structure social networks across domains of cooperation? An exploration of gendered networks among matrilineal and patrilineal Mosuo

   https://doi.org/10.1098/rstb.2021.0436  

   Mattison, Siobhán M. ; MacLaren, Neil G. ; Sum, Chun-Yi ; Shenk, Mary K. ; Blumenfield, Tami ; Wander, Katherine ( January 2023 , Philosophical Transactions of the Royal Society B: Biological Sciences)

   Cooperative networks are essential features of human society. Evolutionary theory hypothesizes that networks are used differently by men and women, yet the bulk of evidence supporting this hypothesis is based on studies conducted in a limited range of contexts and on few domains of cooperation. In this paper, we compare individual-level cooperative networks from two communities in Southwest China that differ systematically in kinship norms and institutions—one matrilineal and one patrilineal—while sharing an ethnic identity. Specifically, we investigate whether network structures differ based on prevailing kinship norms and type of gendered cooperative activity, one woman-centred (preparation of community meals) and one man-centred (farm equipment lending). Our descriptive results show a mixture of ‘feminine’ and ‘masculine’ features in all four networks. The matrilineal meals network stands out in terms of high degree skew. Exponential random graph models reveal a stronger role for geographical proximity in patriliny and a limited role of affinal relatedness across all networks. Our results point to the need to consider domains of cooperative activity alongside gender and cultural context to fully understand variation in how women and men leverage social relationships toward different ends.

   This article is part of the theme issue ‘Cooperation among women: evolutionary and cross-cultural perspectives’.

    

   more » « less
3. Laplacian networks: bounding indicator function smoothness for neural networks robustness

   https://doi.org/10.1017/ATSIP.2021.2  

   Lassance, Carlos ; Gripon, Vincent ; Ortega, Antonio ( January 2021 , APSIPA Transactions on Signal and Information Processing)

   null (Ed.)

   For the past few years, deep learning (DL) robustness (i.e. the ability to maintain the same decision when inputs are subject to perturbations) has become a question of paramount importance, in particular in settings where misclassification can have dramatic consequences. To address this question, authors have proposed different approaches, such as adding regularizers or training using noisy examples. In this paper we introduce a regularizer based on the Laplacian of similarity graphs obtained from the representation of training data at each layer of the DL architecture. This regularizer penalizes large changes (across consecutive layers in the architecture) in the distance between examples of different classes, and as such enforces smooth variations of the class boundaries. We provide theoretical justification for this regularizer and demonstrate its effectiveness to improve robustness on classical supervised learning vision datasets for various types of perturbations. We also show it can be combined with existing methods to increase overall robustness. 

   more » « less
4. Exploring High-Level Neural Networks Architectures for Efficient Spiking Neural Networks Implementation

   https://doi.org/10.1109/ICREST57604.2023.10070080  

   Islam, Riadul ; Majurski, Patrick ; Kwon, Jun ; Tummala, Sri Ranga ( January 2023 , International Conference on Robotics, Electrical and Signal Processing Techniques (ICREST))
5. Degree Centrality Algorithms for Homogeneous Multilayer Networks [Degree Centrality Algorithms for Homogeneous Multilayer Networks]

   https://doi.org/10.5220/0011528900003335  

   Pavel, Hamza ; Santra, Abhishek ; Chakravarthy, Sharma ( October 2022 , knowledge discovery and information retrieval)

   Frans Coenen, Ana L. (Ed.)