Multi-scale receptive fields: Graph attention neural network for hyperspectral image classification

Y Ding, Z Zhang, X Zhao, D Hong, W Cai… - Expert Systems with …, 2023 - Elsevier
Hyperspectral image (HSI) classification has attracted wide attention in many fields.
Applying Graph Neural Network (GNN) to HSI classification is one of the research frontiers …

Multireceptive field: An adaptive path aggregation graph neural framework for hyperspectral image classification

Z Zhang, Y Ding, X Zhao, L Siye, N Yang, Y Cai… - Expert Systems with …, 2023 - Elsevier
In recent years, the applications of graph convolutional networks (GCNs) in hyperspectral
image (HSI) classification have attracted much attention. However, hyperspectral …

Learning knowledge graph embedding with a dual-attention embedding network

H Fang, Y Wang, Z Tian, Y Ye - Expert Systems with Applications, 2023 - Elsevier
Abstract Knowledge Graph Embedding (KGE) aims to retain the intrinsic structural
information of knowledge graphs (KGs) via representation learning, which is critical for …

Robust graph learning with graph convolutional network

Y Wan, C Yuan, M Zhan, L Chen - Information Processing & Management, 2022 - Elsevier
Graph convolutional network (GCN) is a powerful tool to process the graph data and has
achieved satisfactory performance in the task of node classification. In general, GCN uses a …

SGCN: A scalable graph convolutional network with graph-shaped kernels and multi-channels

Z Huang, W Zhou, K Li, Z Jia - Knowledge-Based Systems, 2023 - Elsevier
Graph neural networks (GNNs) have demonstrated great success in graph processing.
However, current message-passing-based GNNs have limitations in terms of feature …

{TYGR}: Type Inference on Stripped Binaries using Graph Neural Networks

C Zhu, Z Li, A Xue, AP Bajaj, W Gibbs, Y Liu… - 33rd USENIX Security …, 2024 - usenix.org
Binary type inference is a core research challenge in binary program analysis and reverse
engineering. It concerns identifying the data types of registers and memory values in a …

MC-GAT: multi-channel graph attention networks for capturing diverse information in complex graphs

Z La, Y Qian, H Leng, T Gu, W Gong, J Chen - Cognitive Computation, 2024 - Springer
Graph attention networks (GAT), which have strong performance in tackling various
analytical tasks on network data, have attracted wide attention. However, complex real-world …

Multi-strategy adaptive data augmentation for Graph Neural Networks

X Juan, X Liang, H Xue, X Wang - Expert Systems with Applications, 2024 - Elsevier
Abstract While existing Graph Neural Networks (GNNs) have demonstrated exceptional
performance in semi-supervised learning, they are criticized for not fully utilizing unlabeled …

Graph Convolutional Network Design for Node Classification Accuracy Improvement

MAS Sejan, MH Rahman, MA Aziz, JI Baik, YH You… - Mathematics, 2023 - mdpi.com
Graph convolutional networks (GCNs) provide an advantage in node classification tasks for
graph-related data structures. In this paper, we propose a GCN model for enhancing the …

[HTML][HTML] Probabilistic Graph Networks for Learning Physics Simulations

SKA Prakash, C Tucker - Journal of Computational Physics, 2024 - Elsevier
Inductive biases play a critical role in enabling Graph Networks (GN) to learn particle and
mesh-based physics simulations. In this paper, we propose two generalizable inductive …