Results 11 to 20 of about 36,148 (258)

Graphs, Convolutions, and Neural Networks: From Graph Filters to Graph Neural Networks

IEEE Signal Processing Magazine, 2020
Network data can be conveniently modeled as a graph signal, where data values are assigned to nodes of a graph that describes the underlying network topology. Successful learning from network data is built upon methods that effectively exploit this graph structure.
Fernando Gama, Elvin Isufi, Geert Leus, Alejandro Ribeiro   +3 more
  +9 more sources

Graph-Time Convolutional Neural Networks

2021 IEEE Data Science and Learning Workshop (DSLW), 2021
Spatiotemporal data can be represented as a process over a graph, which captures their spatial relationships either explicitly or implicitly. How to leverage such a structure for learning representations is one of the key challenges when working with graphs. In this paper, we represent the spatiotemporal relationships through product graphs and develop
Isufi, E. (author), Mazzola, Gabriele (author)   +1 more
openaire   +4 more sources

Graph Neural Networks with Convolutional ARMA Filters [PDF]

IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021
Popular graph neural networks implement convolution operations on graphs based on polynomial spectral filters. In this paper, we propose a novel graph convolutional layer inspired by the auto-regressive moving average (ARMA) filter that, compared to polynomial ones, provides a more flexible frequency response, is more robust to noise, and better ...
Filippo Maria Bianchi, Daniele Grattarola, Lorenzo Livi, Cesare Alippi   +3 more
openaire   +3 more sources

Geometric Deep Learning for Protein–Protein Interaction Predictions

IEEE Access, 2022
This work introduces novel approaches, based on geometrical deep learning, for predicting protein–protein interactions. A dataset containing both interacting and non-interacting proteins is selected from the Negatome Database.
Gabriel St-Pierre Lemieux, Eric Paquet, Herna L Viktor, Wojtek Michalowski   +3 more
doaj   +1 more source

Hybrid Graph Models for Traffic Prediction

Applied Sciences, 2023
Obtaining accurate road conditions is crucial for traffic management, dynamic route planning, and intelligent guidance services. The complex spatial correlation and nonlinear temporal dependence pose great challenges to obtaining accurate road conditions.
Renyi Chen, Huaxiong Yao
doaj   +1 more source

Graph matching as a graph convolution operator for graph neural networks [PDF]

Pattern Recognition Letters, 2021
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, Raveaux, Romain, Conte, Donatello, Venturini, Gilles   +3 more
openaire   +2 more sources

Convolutional Neural Network Outperforms Graph Neural Network on the Spatially Variant Graph Data

Mathematics, 2023
Applying machine learning algorithms to graph-structured data has garnered significant attention in recent years due to the prevalence of inherent graph structures in real-life datasets.
Anna Boronina, Vladimir Maksimenko, Alexander E. Hramov   +2 more
doaj   +1 more source

Pooling in Graph Convolutional Neural Networks [PDF]

2019 53rd Asilomar Conference on Signals, Systems, and Computers, 2019
5 pages, 2 figures, 2019 Asilomar Conference ...
Mark Cheung, John Shi, Lavender Yao Jiang, Oren Wright, José M. F. Moura   +4 more
openaire   +2 more sources

Multipath Graph Convolutional Neural Networks

CoRR, 2021
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, Bikram Boote, Sumanta Bhattacharya, Ujjwal Maulik   +3 more
openaire   +2 more sources

Review of Node Classification Methods Based on Graph Convolutional Neural Networks [PDF]

Jisuanji kexue
Node classification is one of the important research tasks in graph field.In recent years,with the continuous deepening of research on graph convolutional neural network,significant progress has been made in the research and application of node ...
ZHANG Liying, SUN Haihang, SUN Yufa , SHI Bingbo
doaj   +1 more source