Results 51 to 60 of about 9,290 (165)

LPS-GNN: Deploying Graph Neural Networks on Graphs with 100-Billion Edges

open access: yesACM Transactions on Knowledge Discovery from Data
Graph Neural Networks (GNNs) have emerged as powerful tools for various graph mining tasks, yet existing scalable solutions often struggle to balance execution efficiency with prediction accuracy. These difficulties stem from iterative message-passing techniques, which place significant computational demands and require extensive Graphics Processing ...
Xu Cheng   +8 more
openaire   +2 more sources

XGA-E: an explainability-enhanced graph neural network for network traffic anomaly detection

open access: yesCybersecurity
Graph neural network (GNN) have demonstrated excellent performance in network traffic anomaly detection research. However, existing GNN-based approaches often lack interpretability, and their detection performance remains to be improved. To address these
Min Yang, Caiming Liu
doaj   +1 more source

Reconstruction of Radio Environment Map Based on Multi-Source Domain Adaptive of Graph Neural Network for Regression

open access: yesSensors
The graph neural network (GNN) has shown outstanding performance in processing unstructured data. However, the downstream task performance of GNN strongly depends on the accuracy of data graph structural features and, as a type of deep learning (DL ...
Xiaomin Wen   +2 more
doaj   +1 more source

Graph neural network-tracker: a graph neural network-based multi-sensor fusion framework for robust unmanned aerial vehicle tracking

open access: yesVisual Computing for Industry, Biomedicine, and Art
Unmanned aerial vehicle (UAV) tracking is a critical task in surveillance, security, and autonomous navigation applications. In this study, we propose graph neural network-tracker (GNN-tracker), a novel GNN-based UAV tracking framework that effectively ...
Karim Dabbabi, Tijeni Delleji
doaj   +1 more source

Enhanced exploration in reinforcement learning using graph neural network based intrinsic reward mechanism

open access: yesScientific Reports
We propose a Graph Neural Network-based Intrinsic Reward Learning (GNN-IRL) framework to address the exploration–exploitation trade-off in Reinforcement Learning (RL). This approach leverages the structural modeling capabilities of Graph Neural Networks (
J. Arun Pandian   +2 more
doaj   +1 more source

Prototype-Guided Attention for Graph Neural Networks

open access: yesApplied Sciences
The graph neural network (GNN) has demonstrated strong performance in modelling graph-structured data across multiple application domains. However, existing GNN models do not fully exploit the information inherent in data.
Yiran Sun, Hak-Keung Lam
doaj   +1 more source

Communication-Aware Graph Neural Network for Multi-Agent Reinforcement Learning

open access: yesIEEE Access
Multi-agent reinforcement learning (MARL) requires effective communication strategies to solve complex control tasks over uncertain communication channels.
Youngrok Choi   +2 more
doaj   +1 more source

AGS-GNN: Attribute-guided Sampling for Graph Neural Networks

open access: yesProceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
The paper has been accepted to KDD'24 in the research ...
Siddhartha Shankar Das   +4 more
openaire   +3 more sources

Home - About - Disclaimer - Privacy