Results 101 to 110 of about 4,261,155 (305)
Graph-level Neural Networks: Current Progress and Future Directions [PDF]
Graph-structured data consisting of objects (i.e., nodes) and relationships among objects (i.e., edges) are ubiquitous. Graph-level learning is a matter of studying a collection of graphs instead of a single graph.
Wu, Jia +8 more
core +1 more source
Graph neural networks are well suited for physics based simulation. Among other features, graphs can accurately represent thermal effects, with energy conservation operating on the nodes (vertices) and heat flow coursing through edges.
Pierre Hembert +3 more
doaj +1 more source
Graph Structure of Neural Networks
Neural networks are often represented as graphs of connections between neurons. However, despite their wide use, there is currently little understanding of the relationship between the graph structure of the neural network and its predictive performance.
Jiaxuan You +3 more
openaire +3 more sources
Graph stochastic neural networks for semi-supervised learning
Graph Neural Networks (GNNs) have achieved remarkable performance in the task of the semi-supervised node classification. However, most existing models learn a deterministic classification function, which lack sufficient flexibility to explore better ...
Wang, H +5 more
core
ABSTRACT Background Biallelic FIG4 variants classically cause distinct conditions characterized by peripheral neuropathy (Charcot‐Marie‐Tooth disease type 4J) or skeletal dysplasia (Yunis‐Varón syndrome). However, central nervous system involvement is increasingly recognized. The prevalence and specific characteristics of movement disorders within FIG4‐
Andrea Gangfuß +22 more
wiley +1 more source
In this study, we adapt three spatial-temporal graph neural network models to the unique characteristics of crude oil, gold, and silver markets for forecasting purposes.
Parisa Foroutan, Salim Lahmiri
doaj +1 more source
Hierarchical Graph Neural Networks
Over the recent years, Graph Neural Networks have become increasingly popular in network analytic and beyond. With that, their architecture noticeable diverges from the classical multi-layered hierarchical organization of the traditional neural networks.
openaire +3 more sources
Four‐Year Cognitive Outcomes in Multiple Sclerosis: Associations With Lesion Myelin Integrity
ABSTRACT Objectives Cognitive impairment is prevalent in patients with multiple sclerosis (MS) but whether lesion myelin integrity influences future cognitive outcomes remains unclear. We investigated the relationship between baseline lesion myelin water fraction (MWF) and cognitive performance 4 years later.
Iliana Pliska‐Bloch +9 more
wiley +1 more source
AAGCN: a graph convolutional neural network with adaptive feature and topology learning
In recent years, there has been a growing prevalence of deep learning in various domains, owing to advancements in information technology and computing power.
Bin Wang +3 more
doaj +1 more source
A Comparison between Recursive Neural Networks and Graph Neural Networks
Recursive neural networks (RNNs) and graph neural networks (GNNs) are two connectionist models that can directly process graphs. RNNs and GNNs exploit a similar processing framework, but they can be applied to different input domains.
V. Di Massa +17 more
core +1 more source

