Results 31 to 40 of about 6,698,922 (291)

Convolutional Graph Neural Networks

open access: yes2019 53rd Asilomar Conference on Signals, Systems, and Computers, 2019
Convolutional neural networks (CNNs) restrict the, otherwise arbitrary, linear operation of neural networks to be a convolution with a bank of learned filters. This makes them suitable for learning tasks based on data that exhibit the regular structure of time signals and images.
Fernando Gama   +3 more
openaire   +4 more sources

Adaptive filters in Graph Convolutional Neural Networks

open access: yesPattern Recognition, 2023
Over the last few years, we have witnessed the availability of an increasing data generated from non-Euclidean domains, which are usually represented as graphs with complex relationships, and Graph Neural Networks (GNN) have gained a high interest because of their potential in processing graph-structured data.
Andrea Apicella   +3 more
openaire   +4 more sources

Graph MADDPG with RNN for multiagent cooperative environment

open access: yesFrontiers in Neurorobotics, 2023
Multiagent systems face numerous challenges due to environmental uncertainty, with scalability being a critical issue. To address this, we propose a novel multi-agent cooperative model based on a graph attention network.
Xiaolong Wei   +6 more
doaj   +1 more source

Self-organizing incremental and graph convolution neural network for English implicit discourse relation recognition

open access: yesEAI Endorsed Transactions on Scalable Information Systems, 2021
Implicit discourse relation recognition is a sub-task of discourse relation recognition, which is challenging because it is difficult to learn the argument representation with rich semantic information and interactive information. To solve this problem,
Yubo Geng
doaj   +1 more source

A Convolutional Neural Network into graph space

open access: yesCoRR, 2020
arXiv admin note: text overlap with arXiv:1611.08402 by other ...
Maxime Martineau   +3 more
openaire   +3 more sources

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

Anomaly detection with convolutional Graph Neural Networks [PDF]

open access: yesJournal of High Energy Physics, 2021
Abstract We devise an autoencoder based strategy to facilitate anomaly detection for boosted jets, employing Graph Neural Networks (GNNs) to do so. To overcome known limitations of GNN autoencoders, we design a symmetric decoder capable of simultaneously reconstructing edge features and node features. Focusing on latent space based
Atkinson, Oliver   +4 more
openaire   +6 more sources

Phase transitions and optimal algorithms for semisupervised classifications on graphs: From belief propagation to graph convolution network

open access: yesPhysical Review Research, 2020
We perform theoretical and algorithmic studies for the problem of clustering and semisupervised classification on graphs with both pairwise relational information and single-point attribute information, upon a joint stochastic block model for synthetic ...
Pengfei Zhou, Tianyi Li, Pan Zhang
doaj   +1 more source

Graph Coarsening via Convolution Matching for Scalable Graph Neural Network Training [PDF]

open access: yes, 2023
Graph summarization as a preprocessing step is an effective and complementary technique for scalable graph neural network (GNN) training. In this work, we propose the Coarsening Via Convolution Matching (CONVMATCH) algorithm and a highly scalable variant,
Zhu, Jiong   +5 more
core  

Spatial-Temporal Adaptive Graph Convolution with Attention Network for Traffic Forecasting [PDF]

open access: yes, 2022
Traffic forecasting is one canonical example of spatial-temporal learning task in Intelligent Traffic System. Existing approaches capture spatial dependency with a pre-determined matrix in graph convolution neural operators.
Ang, Li   +4 more
core   +1 more source

Home - About - Disclaimer - Privacy