Results 91 to 100 of about 110,849 (310)

Predicting flux in Discrete Fracture Networks via Graph Informed Neural Networks [PDF]

, 2021
Discrete Fracture Network (DFN) flow simulations are commonly used to determine the outflow in fractured media for critical applications. Here, we extend the formulation of spatial graph neural networks with a new architecture, called Graph-Informed ...
Pieraccini, Sandra, Berrone, Stefano, Vaccarino, Francesco, Della Santa, Francesco, Mastropietro, Antonio   +4 more
core  

A Survey on Graph Neural Networks

IEEE Access
Graph Neural Networks (GNNs) have emerged as a fundamental class of models for analyzing graph-structured data, with broad applications spanning social networks, computational neuroscience, and intelligent transportation systems. In contrast to Euclidean data, graphs pose distinctive challenges due to their irregular topology, permutation invariance ...
Xinyang Zhang, Shengrong Li, Haoran Li 0024, Peiliang Gong, Jiahua Shi, Jun Shen 0001, Chunwei Tian, Daoqiang Zhang, Qi Zhu 0001   +8 more
openaire   +3 more sources

Graph Structure of Neural Networks

CoRR, 2020
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, Jure Leskovec, Kaiming He, Saining Xie   +3 more
openaire   +3 more sources

Structure–Function Decoupling of the Sensorimotor and Default Mode Networks in Black Americans With MS

Annals of Clinical and Translational Neurology, EarlyView.
ABSTRACT Background and Objectives Multiple sclerosis (MS) exhibits racially disparate rates of disease progression. Black people with MS (B‐PwMS) experience a more severe disease course than non‐Hispanic White people with MS (NHW‐PwMS). Here we investigated structural and functional connectivity as well as structure–function decoupling in the ...
Emilio Cipriano, Giacomo Boffa, Maria Petracca, Marta Ponzano, Nicole Graziano, Claire Wigley, Claire Riley, Jonathan Howard, Pietro Bontempi, Sylvia Klineova, Fred Lublin, Matilde Inglese   +11 more
wiley   +1 more source

Hierarchical Graph Neural Networks

CoRR, 2021
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   +2 more sources

Baseline Regional Cholinergic Denervation Predicts Cognitive Trajectories in Moderate Parkinson Disease

Annals of Clinical and Translational Neurology, EarlyView.
ABSTRACT Objective Cognitive decline is a disabling and variable feature of Parkinson disease (PD). While cholinergic system degeneration is linked to cognitive impairments in PD, most prior research reported cross‐sectional associations. We aimed to fill this gap by investigating whether baseline regional cerebral vesicular acetylcholine transporter ...
Taylor Brown, Giulia Carli, Prabesh Kanel, Stiven Roytman, Jaimie Barr, Nicolaas I. Bohnen, Roger L. Albin   +6 more
wiley   +1 more source

AAGCN: a graph convolutional neural network with adaptive feature and topology learning

Scientific Reports
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, Bodong Cai, Jinfang Sheng, Wenzhe Jiao   +3 more
doaj   +1 more source

A Comparison between Recursive Neural Networks and Graph Neural Networks

, 2006
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, Lorenzo Sarti, L. Sarti, Marco Maggini, G. Monfardini, Vincenzo Di Massa, Scarselli, F., Di Massa, V., Marco Gori, F. Scarselli, Sarti, L., Monfardini, G., Maggini, M., M. Maggini, Gabriele Monfardini, Franco Scarselli, M. Gori, Gori, M.   +17 more
core   +1 more source

Entity alignment via graph neural networks: a component-level study

, 2023
Entity alignment plays an essential role in the integration of knowledge graphs (KGs) as it seeks to identify entities that refer to the same real-world objects across different KGs.
Shu, Yanfeng, Zhang, Ji, Chi, Chi-Hung, Huang, Guangyan, He, Jing   +4 more
core   +1 more source

A Depolarizing Leak in Sodium Bicarbonate Cotransporter NBCe1 Causes Brain Edema

Annals of Clinical and Translational Neurology, EarlyView.
ABSTRACT Objectives SLC4A4 encodes electrogenic sodium bicarbonate cotransporter NBCe1, prominently expressed in kidney and brain. Recessive loss‐of‐function variants in SLC4A4 cause proximal renal tubular acidosis, no brain edema. In the brain, NBCe1 is expressed by astrocytes, where it regulates pH and mediates astrocyte volume changes.
Quinty Bisseling, Mark D. Parker, Sven Kerst, Richard A. Pasternack, Jacob Tondreau, Marjolein Breur, Gemma M. van Rooijen‐van Leeuwen, Davide Tonduti, Ettore Salsano, Alejandra Darling, Joanna A. E. van Wijk, Susanna Törnroth‐Horsefield, Marianna Bugiani, Petra J. W. Pouwels, Quinten Waisfisz, Marjo S. van der Knaap, Rogier Min   +16 more
wiley   +1 more source