Remote sensing scene classification based on high-order graph convolutional network
Y Gao, J Shi, J Li, R Wang - European Journal of Remote Sensing, 2021 - Taylor & Francis
Remote sensing scene classification has gained increasing interest in remote sensing
image understanding and feature representation is the crucial factor for classification …
image understanding and feature representation is the crucial factor for classification …
Node classification using kernel propagation in graph neural networks
SKA Prakash, CS Tucker - Expert Systems with Applications, 2021 - Elsevier
In this work, we introduce a kernel propagation method that enables graph neural networks
(GNNs) to leverage higher-order network structural information without increasing the …
(GNNs) to leverage higher-order network structural information without increasing the …
Multihop neighbor information fusion graph convolutional network for text classification
Graph convolutional network (GCN) is an efficient network for learning graph
representations. However, it costs expensive to learn the high‐order interaction …
representations. However, it costs expensive to learn the high‐order interaction …
Hierarchical attention networks for medical image segmentation
F Ding, G Yang, J Liu, J Wu, D Ding, J Xv… - arXiv preprint arXiv …, 2019 - arxiv.org
The medical image is characterized by the inter-class indistinction, high variability, and
noise, where the recognition of pixels is challenging. Unlike previous self-attention based …
noise, where the recognition of pixels is challenging. Unlike previous self-attention based …
Hybrid Low‐Order and Higher‐Order Graph Convolutional Networks
With the higher‐order neighborhood information of a graph network, the accuracy of graph
representation learning classification can be significantly improved. However, the current …
representation learning classification can be significantly improved. However, the current …
Community detection in feature-rich networks using data recovery approach
B Mirkin, S Shalileh - Journal of Classification, 2022 - Springer
The problem of community detection in a network with features at its nodes takes into
account both the graph structure and node features. The goal is to find relatively dense …
account both the graph structure and node features. The goal is to find relatively dense …
HDGCN: Dual-channel graph convolutional network with higher-order information for robust feature learning
Graph convolutional network (GCN) algorithms have been employed to learn graph
embedding due to its inductive inference property, which is extended to GCN with higher …
embedding due to its inductive inference property, which is extended to GCN with higher …
Graph convolutional networks with higher‐order pooling for semisupervised node classification
F Lei, X Liu, J Jiang, L Liao, J Cai… - … Practice and Experience, 2022 - Wiley Online Library
The information propagation mechanism in graph‐structured networks such as social
networks is the foundation of network security. The graph convolutional network (GCN) is a …
networks is the foundation of network security. The graph convolutional network (GCN) is a …
Inductive Biases in Graph Representation Learning
SKA Prakash - 2023 - search.proquest.com
Abstract Graph Networks (GNs) have emerged as essential machine learning tools for
reasoning about how entities in complex systems interact. They support dynamical systems …
reasoning about how entities in complex systems interact. They support dynamical systems …
Graph mining on static, multiplex and attributed networks
B Rózemberczki - 2021 - era.ed.ac.uk
Graph structured data is pervasive and generated by online human interactions at an
unprece-dented velocity. Sophisticated features encoded by relational data, such as …
unprece-dented velocity. Sophisticated features encoded by relational data, such as …