Graph attention networks - Open Access .click

Results 91 to 100 of about 6,341,676 (193)

Graph Attention Diffusion Method Combining Diffusion Mechanism and Graph Attention Mechanism

Algorithms
Graph neural networks have attracted much attention and performed well in many downstream tasks. However, due to issues such as oversmoothing, existing graph neural networks are limited in their ability to quantitatively exploit higher-order neighborhood
Xing Li +7 more
doaj +1 more source

MEGAN: Multi-explanation Graph Attention Network

, 2023
We propose a multi-explanation graph attention network (MEGAN). Unlike existing graph explainability methods, our network can produce node and edge attributional explanations along multiple channels, the number of which is independent of task specifications.
Jonas Teufel +3 more
openaire +5 more sources

Attention Graph Convolution Network for Image Segmentation in Big SAR Imagery Data

Remote Sensing, 2019
The recent emergence of high-resolution Synthetic Aperture Radar (SAR) images leads to massive amounts of data. In order to segment these big remotely sensed data in an acceptable time frame, more and more segmentation algorithms based on deep learning ...
Fei Ma +4 more
doaj +1 more source

Text Summarization With Graph Attention Networks

CoRR
This study aimed to leverage graph information, particularly Rhetorical Structure Theory (RST) and Co-reference (Coref) graphs, to enhance the performance of our baseline summarization models. Specifically, we experimented with a Graph Attention Network architecture to incorporate graph information.
Mohammadreza Ardestani, Yllias Chali
openaire +4 more sources

Accelerating Transistor Simulations With Self-Supervised Graph Attention Networks

IEEE Access
Technology CAD (TCAD) tools are pivotal for transistor modeling, enabling physics-based simulations with high accuracy essential for developing next-generation technology nodes. However, their high computational cost and low throughput severely constrain
Tarek Mohamed, Hussam Amrouch
doaj +1 more source

EATSA-GNN: Edge-Aware and Two-Stage attention for enhancing graph neural networks based on teacher–student mechanisms for graph node classification

Graph Neural Networks (GNNs) have fundamentally transformed the way in which we handle and examine data originating from non-Euclidean domains. Traditional approaches to imbalanced node classification problems, such as resampling, are ineffective because
Fofanah, Abdul Joseph, Leigh, Alpha Omar
core +1 more source

Flow-Attentional Graph Neural Networks

Trans. Mach. Learn. Res.
Accepted @ Transactions on Machine Learning Research (TMLR): https://openreview.net/forum?id ...
Pascal Plettenberg +3 more
openaire +3 more sources

Joint Entity-Relation Extraction via Improved Graph Attention Networks

, 2020
Joint named entity recognition and relation extraction is an essential natural language processing task that aims to identify entities and extract the corresponding relations in an end-to-end manner. At present, compared with the named entity recognition
Qinghan Lai, Zihan Zhou, Song Liu
core +1 more source

Graph-aware isomorphic attention for adaptive dynamics in transformers

APL Machine Learning
We present an approach for modifying transformer architectures by integrating graph-aware relational reasoning into the attention mechanism, merging concepts from graph neural networks and language modeling ...
Markus J. Buehler
doaj +1 more source

Spiking Heterogeneous Graph Attention Networks

Proceedings of the AAAI Conference on Artificial Intelligence
Real-world graphs or networks are usually heterogeneous, involving multiple types of nodes and relationships. Heterogeneous graph neural networks (HGNNs) can effectively handle these diverse nodes and edges, capturing heterogeneous information within the graph, thus exhibiting outstanding performance.
Buqing Cao +5 more
openaire +2 more sources

graph neural networks
attention mechanism
graph neural network

deep learning
graph attention network
node classification