Results 91 to 100 of about 6,693,998 (303)

k-Nearest Neighbor Learning with Graph Neural Networks

open access: yesMathematics, 2021
k-nearest neighbor (kNN) is a widely used learning algorithm for supervised learning tasks. In practice, the main challenge when using kNN is its high sensitivity to its hyperparameter setting, including the number of nearest neighbors k, the distance ...
Seokho Kang
doaj   +1 more source

A Survey on Graph Neural Networks

open access: yesIEEE 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   +8 more
openaire   +4 more sources

Research Progress of Graph Neural Network Using Edge Information [PDF]

open access: yesJisuanji kexue yu tansuo
Graph neural network is a deep learning technique that can process non-Euclidean structured complex data which can be transformed into graphs. In recent years, it has received a lot of research attention, providing a new research perspective and powerful
ZHU Tao, GAO Guangliang, WANG Qun, XIA Lingling, LIANG Guangjun, MA Zhuo
doaj   +1 more source

Blood RNA Biomarker Signatures for Early Diagnosis and Prognosis in Ischemic and Hemorrhagic Stroke: The IBIS‐CT1 Study

open access: yesAnnals of Clinical and Translational Neurology, EarlyView.
ABSTRACT Objective To evaluate the expression of nine blood RNA biomarkers in a clinical trial based on genes previously identified in an experimental monkey model of stroke for diagnosis feasibility and prognostication. Methods IBIS‐CT1 was a prospective longitudinal study enrolling patients with ischemic stroke (IS) or intracerebral hemorrhage (ICH ...
Salomé Retailleau   +11 more
wiley   +1 more source

Graph neural network structural limitation for thermal simulation and architecture optimization through rating system

open access: yesAdvanced Modeling and Simulation in Engineering Sciences
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

Research on few-shot text classification techniques based on text-level-graph neural networks [PDF]

open access: yesJournal of Hebei University of Science and Technology
In order to solve the problem of poor accuracy of text classification in text graph neural network with small samples, a text level graph neural network-prototypical (LGNN-Proto) was designed.
Xiangcheng AN, Baozhu LIU, Jingwei GAN
doaj   +1 more source

Graph Structure of Neural Networks

open access: yesCoRR, 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   +3 more
openaire   +3 more sources

Node Classification on The Citation Network Using Graph Neural Network

open access: yes, 2023
Research on Graph Neural Networks has influenced various current real-world problems. The graph-based approach is considered capable of effectively representing the actual state of surrounding data by utilizing nodes, edges, and features.
Bambang Riyanto Trilaksono   +1 more
core   +1 more source

Stage‐Specific Patterns of Imaging and Non‐Motor Biomarkers in Spinocerebellar Ataxia Type 3

open access: yesAnnals of Clinical and Translational Neurology, EarlyView.
ABSTRACT Objective Advancements in disease‐modifying therapies for spinocerebellar ataxia Type 3 (SCA3) underscore the need for robust biomarkers to monitor disease progression and evaluate treatment efficacy. Although motor phenotypes have been well characterized, less is known about non‐motor and imaging‐based features across different disease stages.
Chun Li   +17 more
wiley   +1 more source

A graph neural network with negative message passing and uniformity maximization for graph coloring

open access: yesComplex & Intelligent Systems
Graph neural networks have received increased attention over the past years due to their promising ability to handle graph-structured data, which can be found in many real-world problems such as recommender systems and drug synthesis.
Xiangyu Wang, Xueming Yan, Yaochu Jin
doaj   +1 more source

Home - About - Disclaimer - Privacy