Results 51 to 60 of about 4,261,155 (305)

A Review of Graph Neural Networks and Their Applications in Power Systems

open access: yesJournal of Modern Power Systems and Clean Energy, 2022
Deep neural networks have revolutionized many machine learning tasks in power systems, ranging from pattern recognition to signal processing. The data in these tasks are typically represented in Euclidean domains.
Wenlong Liao   +4 more
doaj   +1 more source

Understanding Pooling in Graph Neural Networks [PDF]

open access: yes, 2021
Inspired by the conventional pooling layers in convolutional neural networks, many recent works in the field of graph machine learning have introduced pooling operators to reduce the size of graphs. The great variety in the literature stems from the many
Grattarola, Daniele   +7 more
core   +1 more source

Advances in Graph Neural Networks for Combinatorial Optimization Problems [PDF]

open access: yesJisuanji kexue yu tansuo
Combinatorial optimization, as an important branch of mathematical optimization, focuses on finding optimal solution within a finite discrete solution space.
ZHU Ye, DING Cangfeng, CAO Bohao, CHEN Kexin
doaj   +1 more source

Graph Neural Networks for Graph Search [PDF]

open access: yesProceedings of the 3rd Joint International Workshop on Graph Data Management Experiences & Systems (GRADES) and Network Data Analytics (NDA), 2020
Graph neural networks (GNNs) have received more and more attention in past several years, due to the wide applications of graphs and networks, and the superiority of their performance compared to traditional heuristics-driven approaches. However, most existing GNNs still focus on node-level applications, such as node classification and link prediction,
openaire   +2 more sources

Automatic Modulation Classification Based on CNN-Transformer Graph Neural Network

open access: yesSensors, 2023
In recent years, neural network algorithms have demonstrated tremendous potential for modulation classification. Deep learning methods typically take raw signals or convert signals into time–frequency images as inputs to convolutional neural networks ...
Dong Wang   +4 more
doaj   +1 more source

Rethinking Graph Regularization for Graph Neural Networks

open access: yesProceedings of the AAAI Conference on Artificial Intelligence, 2021
The graph Laplacian regularization term is usually used in semi-supervised representation learning to provide graph structure information for a model f(X). However, with the recent popularity of graph neural networks (GNNs), directly encoding graph structure A into a model, i.e., f(A, X), has become the more common approach.
Han Yang 0002   +2 more
openaire   +3 more sources

Graph Neural Networks with Adaptive Readouts [PDF]

open access: yes, 2022
An effective aggregation of node features into a graph-level representation via readout functions is an essential step in numerous learning tasks involving graph neural networks.
Oglic D.   +4 more
core  

The Logic of Graph Neural Networks [PDF]

open access: yes2021 36th Annual ACM/IEEE Symposium on Logic in Computer Science (LICS), 2021
Graph neural networks (GNNs) are deep learning architectures for machine learning problems on graphs. It has recently been shown that the expressiveness of GNNs can be characterised precisely by the combinatorial Weisfeiler-Leman algorithms and by finite variable counting logics.
openaire   +3 more sources

Symbolic Hyperdimensional Vectors with Sparse Graph Convolutional Neural Networks

open access: yes, 2022
In this paper, we propose a novel way of representing graphs for processing in Graph Neural Networks. We reduce the dimensionality of the input data by using Random Indexing, a Vector Symbolic Architectural framework; we implement a new trainable neural ...
Karlgren, Jussi,   +3 more
core   +1 more source

STAGCN: Spatial–Temporal Attention Graph Convolution Network for Traffic Forecasting

open access: yesMathematics, 2022
Traffic forecasting plays an important role in intelligent transportation systems. However, the prediction task is highly challenging due to the mixture of global and local spatiotemporal dependencies involved in traffic data.
Yafeng Gu, Li Deng
doaj   +1 more source

Home - About - Disclaimer - Privacy