Results 101 to 110 of about 6,341,676 (193)

Graph Pattern Matching: From Intractable to Polynomial Time [PDF]

, 2010
Graph pattern matching is typically defined in terms of sub-graph isomorphism, which makes it an np-complete problem. Moreover, it requires bijective functions, which are often too restrictive to characterize patterns in emerging applications. We propose
Li, Jianzhong, Tang, Nan, Ma, Shuai, Fan, Wenfei; id_orcid, Wu, Yunpeng, Wu, Yinghui   +5 more
core  

H-GAT: A Hardware-Efficient Accelerator for Graph Attention Networks

Journal of Applied Science and Engineering
Recently, Graph Attention Networks (GATs) have shown good performance for representation learning on graphs. Furthermore, GAT leverage the masked self-attention mechanism to get a more advanced feature representation than the graph convolution networks ...
Shizhen Huang, Enhao Tang, Shun Li
doaj   +1 more source

Link Performance Prediction of Power Fiber Optic Communication System Based on Attention Mechanism and Convolutional Neural Network Fusion

Electrica
In order to enhance the multi-objective optimization capability of power communication transmission networks, the author proposes an optimization method that integrates improved graph neural networks (GNNs) and genetic algorithms (GAs).
Yong Zhang, Yan Liu, Chunying Wang, Jiaojiao Dong   +3 more
doaj   +1 more source

Efficient Graph Generation with Graph Recurrent Attention Networks

CoRR, 2019
We propose a new family of efficient and expressive deep generative models of graphs, called Graph Recurrent Attention Networks (GRANs). Our model generates graphs one block of nodes and associated edges at a time. The block size and sampling stride allow us to trade off sample quality for efficiency.
Renjie Liao 0001, Yujia Li 0001, Yang Song 0011, Shenlong Wang, Charlie Nash, William L. Hamilton, David Duvenaud, Raquel Urtasun, Richard S. Zemel   +8 more
openaire   +2 more sources

GTAT: empowering graph neural networks with cross attention

Scientific Reports
Graph Neural Networks (GNNs) serve as a powerful framework for representation learning on graph-structured data, capturing the information of nodes by recursively aggregating and transforming the neighboring nodes’ representations.
Jiahao Shen, Qura Tul Ain, Yaohua Liu, Banqing Liang, Xiaoli Qiang, Zheng Kou   +5 more
doaj   +1 more source

Multimodal graph neural networks in healthcare: a review of fusion strategies across biomedical domains

Frontiers in Artificial Intelligence
Graph Neural Networks (GNNs) have transformed multimodal healthcare data integration by capturing complex, non-Euclidean relationships across diverse sources such as electronic health records, medical imaging, genomic profiles, and clinical notes.
Maria Vaida, Ziyuan Huang
doaj   +1 more source

Synchronization in random networks with given expected degree sequences [PDF]

, 2008
Synchronization in random networks with given expected degree sequences is studied. We also investigate in details the synchronization in networks whose topology is described by classical random graphs, power-law random graphs and hybrid graphs when N ...
Kocarev, L., Checco, P., Biey, Mario
core  

Graph Neural Networks Exploration

, 2023
Táto práca sa venuje rozboru metód grafových neurónových sietí pre klasifikáciu vrcholov a grafov. Skúma súčasné knižnice na prácu s grafovými neurónovými sieťami ako StellarGraph, PyTorch Geometric a DGL.
Barbara Bobeničová
core  

Channel-Attentive Graph Neural Networks

2024 IEEE International Conference on Data Mining (ICDM)
Graph Neural Networks (GNNs) set the state-of-the-art in representation learning for graph-structured data. They are used in many domains, from online social networks to complex molecules. Most GNNs leverage the message-passing paradigm and achieve strong performances on various tasks.
Tugrul Hasan Karabulut, Inci M. Baytas
openaire   +4 more sources

A graph neural network with negative message passing and uniformity maximization for graph coloring

Complex & Intelligent Systems
Graph neural networks have received increased attention over the past years due to their promising ability to handle graph-structured data, which can be found in many real-world problems such as recommender systems and drug synthesis.
Xiangyu Wang, Xueming Yan, Yaochu Jin
doaj   +1 more source