Redirigiendo al acceso original de articulo en 20 segundos...
Inicio  /  Information  /  Vol: 12 Par: 4 (2021)  /  Artículo
ARTÍCULO
TITULO

Exploring the Value of Nodes with Multicommunity Membership for Classification with Graph Convolutional Neural Networks

Michael Hopwood    
Phuong Pho and Alexander V. Mantzaris    

Resumen

Sampling is an important step in the machine learning process because it prioritizes samples that help the model best summarize the important concepts required for the task at hand. The process of determining the best sampling method has been rarely studied in the context of graph neural networks. In this paper, we evaluate multiple sampling methods (i.e., ascending and descending) that sample based off different definitions of centrality (i.e., Voterank, Pagerank, degree) to observe its relation with network topology. We find that no sampling method is superior across all network topologies. Additionally, we find situations where ascending sampling provides better classification scores, showing the strength of weak ties. Two strategies are then created to predict the best sampling method, one that observes the homogeneous connectivity of the nodes, and one that observes the network topology. In both methods, we are able to evaluate the best sampling direction consistently.

 Artículos similares

       
 
Mingxiang Liu, Lei Zhang, Le Han, Ying Zhang, Chengjun Gu and Jianbo Huang    
Perfluorohexanesulfonic acid (PFHxS) is considered a persistent and harmful substance to ecosystems and human health and should thus be necessarily removed. In this paper, the influence of working pressure, temperature, pH value, initial concentration, a... ver más
Revista: Water

 
Euclides Deago, Marian Ramírez, Kleveer Espino, Daniel Nieto, Maudi Barragán, Max García and Jessica Guevara-Cedeño    
Anaerobic digestion (AD) is usually carried out at mesophilic temperatures (25?45 °C) in most countries, whether in temperate or tropical climates, which results in the need for heat injection and consequently increases costs. In this regard, batch AD te... ver más
Revista: Water

 
Rahmeh Ibrahim, Rawan Ghnemat and Qasem Abu Al-Haija    
Convolutional Neural Networks (CNNs) have exhibited remarkable potential in effectively tackling the intricate task of classifying MRI images, specifically in Alzheimer?s disease detection and brain tumor identification. While CNNs optimize their paramet... ver más
Revista: AI

 
Vikram Puri, Subhra Mondal, Subhankar Das and Vasiliki G. Vrana    
Blockchain and immersive technology are the pioneers in bringing digitalization to tourism, and researchers worldwide are exploring many facets of these techniques. This paper analyzes the various aspects of blockchain technology and its potential use in... ver más
Revista: Informatics

 
Martina Saletta and Claudio Ferretti    
Deep neural networks have proven to be able to learn rich internal representations, including for features that can also be used for different purposes than those the networks are originally developed for. In this paper, we are interested in exploring su... ver más
Revista: Information