Spatial-Temporal Interactive Dynamic Graph Convolution Network for Traffic Forecasting [PDF]
Accurate traffic forecasting is essential for smart cities to achieve traffic control, route planning, and flow detection. Although many spatial-temporal methods are currently proposed, these methods are deficient in capturing the spatial-temporal ...
Zhang, Yaying, Liu, Aoyu
core +1 more source
Graph matching as a graph convolution operator for graph neural networks [PDF]
Abstract Convolutional neural networks (CNNs), in a few decades, have outperformed the existing state of the art methods in classification context. However, in the way they were formalised, CNNs are bound to operate on euclidean spaces. Indeed, convolution is a signal operation that are defined on euclidean spaces.
Martineau, Maxime +3 more
openaire +2 more sources
DRACON: Disconnected Graph Neural Network for Atom Mapping in Chemical Reactions [PDF]
Machine learning solved many challenging problems in computer-assisted synthesis prediction (CASP). We formulate a reaction prediction problem in terms of node-classification in a disconnected graph of source molecules and generalize a graph convolution ...
Filipp, Nikitin +2 more
core +1 more source
An Urban Traffic Flow Fusion Network Based on a Causal Spatiotemporal Graph Convolution Network
Traffic flow prediction is an important part of intelligent transportation systems. In recent years, most methods have considered only the feature relationships of spatial dimensions of traffic flow data, and ignored the feature fusion of spatial and ...
Xing Xu, Hao Mao, Yun Zhao, Xiaoshu Lü
doaj +1 more source
Lixdh12/Hand-Gesture-Recognition-Using-Background-Elllimination-and-Convolution-Neural-Network:
Hand Gesture Recognition using Convolution Neural Network built using Tensorflow, OpenCV and ...
Sparsha Saha, mohammed-Emad
core +1 more source
Research on Accurate Recommendation of Learning Resources based on Graph Neural Networks and Convolutional Algorithms [PDF]
In response to the challenges of learning confusion and information overload in online learning, a personalized learning resource recommendation algorithm based on graph neural networks and convolution is proposed to address the cold start and data ...
3, Yuyi, Wang, SaiNan, 1, Bozhi
core +1 more source
Multipath Graph Convolutional Neural Networks
Las redes de convolución de gráficos han atraído recientemente mucha atención para el aprendizaje de la representación en espacios de características no euclidianos. Investigaciones recientes se han centrado en el apilamiento de múltiples capas como en las redes neuronales convolucionales para el aumento del poder expresivo de las redes de convolución ...
Rangan Das +3 more
openaire +3 more sources
Pooling in Graph Convolutional Neural Networks [PDF]
5 pages, 2 figures, 2019 Asilomar Conference ...
Mark Cheung +4 more
openaire +3 more sources
Convolution operators and the discrete Laplacian [PDF]
PhDIn this thesis, we obtain new results for convolution operators on homogeneous spaces and give applications to the Laplacian on a homogeneous graph. Some of these results have been published in joint papers [13, 14] with my supervisor.
Chen, Chung-Chuan
core +3 more sources
reg-sgc: An open-source software for regularized Simple Graph Convolution
Attributed graphs are powerful tools to represent real-life systems in many domains such as social networks, biological metabolic networks, consumer recommendation systems and more.
Patrick Pho, Alexander V. Mantzaris
doaj +1 more source

