A survey on heterogeneous network representation learning
Y Xie, B Yu, S Lv, C Zhang, G Wang, M Gong - Pattern recognition, 2021 - Elsevier
Heterogeneous information networks usually contain different kinds of nodes and
distinguishing types of relations, which can preserve more information than homogeneous …
distinguishing types of relations, which can preserve more information than homogeneous …
Network analysis reveals the latent structure of negative symptoms in schizophrenia
Prior studies using exploratory factor analysis provide evidence that negative symptoms are
best conceptualized as 2 dimensions reflecting diminished motivation and expression …
best conceptualized as 2 dimensions reflecting diminished motivation and expression …
Interest communities and flow roles in directed networks: the Twitter network of the UK riots
M Beguerisse-Díaz… - Journal of The …, 2014 - royalsocietypublishing.org
Directionality is a crucial ingredient in many complex networks in which information, energy
or influence are transmitted. In such directed networks, analysing flows (and not only the …
or influence are transmitted. In such directed networks, analysing flows (and not only the …
[HTML][HTML] K-core robustness in ecological and financial networks
K Burleson-Lesser, F Morone, MS Tomassone… - Scientific reports, 2020 - nature.com
In many real-world networks, the ability to withstand targeted or global attacks; extinctions; or
shocks is vital to the survival of the network itself, and of dependent structures such as …
shocks is vital to the survival of the network itself, and of dependent structures such as …
Accelerating community detection by using k-core subgraphs
Community detection is expensive, and the cost generally depends at least linearly on the
number of vertices in the graph. We propose working with a reduced graph that has many …
number of vertices in the graph. We propose working with a reduced graph that has many …
Symmetric uncertainty class-feature association map for feature selection in microarray dataset
For a huge number of features versus a small size of samples, feature selection methods are
useful preprocessing approaches that could eliminate the irrelevant and redundant features …
useful preprocessing approaches that could eliminate the irrelevant and redundant features …
[HTML][HTML] Local processing in neurites of VGluT3-expressing amacrine cells differentially organizes visual information
Neurons receive synaptic inputs on extensive neurite arbors. How information is organized
across arbors and how local processing in neurites contributes to circuit function is mostly …
across arbors and how local processing in neurites contributes to circuit function is mostly …
[HTML][HTML] Tracking the main states of dynamic functional connectivity in resting state
Dynamical changes have recently been tracked in functional connectivity (FC) calculated
from resting-state functional magnetic resonance imaging (R-fMRI), when a person is …
from resting-state functional magnetic resonance imaging (R-fMRI), when a person is …
Inclusivity enhances robustness and efficiency of social networks
JM Moore, M Small, G Yan - Physica A: Statistical Mechanics and its …, 2021 - Elsevier
Many modern institutions seek to be inclusive, but the quantitative benefits of this goal are
not always communicated effectively to stakeholders. To facilitate this important dialogue …
not always communicated effectively to stakeholders. To facilitate this important dialogue …
Distance metric learning for complex networks: Towards size-independent comparison of network structures
S Aliakbary, S Motallebi, S Rashidian… - … Journal of Nonlinear …, 2015 - pubs.aip.org
Real networks show nontrivial topological properties such as community structure and long-
tail degree distribution. Moreover, many network analysis applications are based on …
tail degree distribution. Moreover, many network analysis applications are based on …