[HTML][HTML] Networks beyond pairwise interactions: Structure and dynamics
The complexity of many biological, social and technological systems stems from the richness
of the interactions among their units. Over the past decades, a variety of complex systems …
of the interactions among their units. Over the past decades, a variety of complex systems …
Percolation on complex networks: Theory and application
In the last two decades, network science has blossomed and influenced various fields, such
as statistical physics, computer science, biology and sociology, from the perspective of the …
as statistical physics, computer science, biology and sociology, from the perspective of the …
Map** the NFT revolution: market trends, trade networks, and visual features
Abstract Non Fungible Tokens (NFTs) are digital assets that represent objects like art,
collectible, and in-game items. They are traded online, often with cryptocurrency, and are …
collectible, and in-game items. They are traded online, often with cryptocurrency, and are …
Large scale learning on non-homophilous graphs: New benchmarks and strong simple methods
Many widely used datasets for graph machine learning tasks have generally been
homophilous, where nodes with similar labels connect to each other. Recently, new Graph …
homophilous, where nodes with similar labels connect to each other. Recently, new Graph …
Beyond low-frequency information in graph convolutional networks
Graph neural networks (GNNs) have been proven to be effective in various network-related
tasks. Most existing GNNs usually exploit the low-frequency signals of node features, which …
tasks. Most existing GNNs usually exploit the low-frequency signals of node features, which …
Combining label propagation and simple models out-performs graph neural networks
Q Huang, H He, A Singh, SN Lim… - ar**_the_Evolution_of_Social_Research_and_Data_Science_on_30_Years_of_Social_Indicators_Research/links/5e316b7292851c7f7f090200/Map**-the-Evolution-of-Social-Research-and-Data-Science-on-30-Years-of-Social-Indicators-Research.pdf" data-clk="hl=ko&sa=T&oi=gga&ct=gga&cd=7&d=12240797281760792394&ei=Gq-vZ6XrFIqy6rQPl5KnWA" data-clk-atid="Sk_r8kUM4KkJ" target="_blank">[PDF] researchgate.net
Map** the Evolution of Social Research and Data Science on 30 Years of Social Indicators Research
Abstract Social Indicators Research (SIR) year by year has consolidated its preeminent
position in the debate concerning the study of all the aspects of quality of life. The need of a …
position in the debate concerning the study of all the aspects of quality of life. The need of a …
Spectral clustering with graph neural networks for graph pooling
Spectral clustering (SC) is a popular clustering technique to find strongly connected
communities on a graph. SC can be used in Graph Neural Networks (GNNs) to implement …
communities on a graph. SC can be used in Graph Neural Networks (GNNs) to implement …
Adversarial attacks on graph neural networks: Perturbations and their patterns
Deep learning models for graphs have achieved strong performance for the task of node
classification. Despite their proliferation, little is known about their robustness to adversarial …
classification. Despite their proliferation, little is known about their robustness to adversarial …