Results 21 to 30 of about 4,261,155 (305)

Mathematical Expressiveness of Graph Neural Networks

open access: yesMathematics, 2022
Graph Neural Networks (GNNs) are neural networks designed for processing graph data. There has been a lot of focus on recent developments of graph neural networks concerning the theoretical properties of the models, in particular with respect to their ...
Guillaume Lachaud   +2 more
doaj   +1 more source

Network In Graph Neural Network

open access: yesCoRR, 2021
Graph Neural Networks (GNNs) have shown success in learning from graph structured data containing node/edge feature information, with application to social networks, recommendation, fraud detection and knowledge graph reasoning. In this regard, various strategies have been proposed in the past to improve the expressiveness of GNNs.
Xiang Song 0003   +4 more
openaire   +3 more sources

Graph Convolutional Networks with Long-distance Words Dependency in Sentences for Short Text Classification [PDF]

open access: yesJisuanji kexue, 2022
With the wide application of graph neural network technology in the field of natural language processing,the research of text classification based on graph neural networks has received more and more attention.Building graph for text is an important ...
ZHANG Hu, BAI Ping
doaj   +1 more source

Real Quadratic-Form-Based Graph Pooling for Graph Neural Networks

open access: yesMachine Learning and Knowledge Extraction, 2022
Graph neural networks (GNNs) have developed rapidly in recent years because they can work over non-Euclidean data and possess promising prediction power in many real-word applications.
Youfa Liu, Guo Chen
doaj   +1 more source

Explainable Graph Neural Networks for Organic Cages [PDF]

open access: yes, 2021
The development of accurate and explicable machine learning models to predict the properties of topologically complex systems is a challenge in material science.
Qi, Yuan   +2 more
core   +2 more sources

Learning the Network of Graphs for Graph Neural Networks

open access: yesCoRR, 2022
Graph neural networks (GNNs) have achieved great success in many scenarios with graph-structured data. However, in many real applications, there are three issues when applying GNNs: graphs are unknown, nodes have noisy features, and graphs contain noisy connections. Aiming at solving these problems, we propose a new graph neural network named as GL-GNN.
Yixiang Shan   +5 more
openaire   +2 more sources

Stochastic Graph Neural Networks [PDF]

open access: yesICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020
Graph neural networks (GNNs) model nonlinear representations in graph data with applications in distributed agent coordination, control, and planning among others. Current GNN architectures assume ideal scenarios and ignore link fluctuations that occur due to environment, human factors, or external attacks. In these situations, the GNN fails to address
Zhan Gao, Elvin Isufi, Alejandro Ribeiro
openaire   +4 more sources

Schatten Graph Neural Networks

open access: yesIEEE Access, 2022
Graph Neural Networks (GNNs) have been intensively studied in recent years because of their promising performance over graph-structural data and have provided assistance in many fields.
Youfa Liu   +3 more
doaj   +1 more source

Graph neural networks for prediction of protein isoelectric points [PDF]

open access: yes, 2022
Graph neural networks were used to model protein isoelectric points. Predictions contained markedly fewer outliers (predicted with errors > 0.5 pH units) compared to tools published in the literature, despite slightly higher root-mean-squared errors ...
Tom, Brenner
core   +1 more source

Graph Coordinates and Conventional Neural Networks - An Alternative for Graph Neural Networks

open access: yes2023 IEEE International Conference on Big Data (BigData), 2023
This paper is submitted and will be published on Big Data Conference 2023, Data-driven Science for Graphs: Algorithms, Architectures, and Application ...
Zheyi Qin   +2 more
openaire   +2 more sources

Home - About - Disclaimer - Privacy