Results 161 to 170 of about 2,166 (199)

The detection of isomorphism of networks described by Reference Graphs

2020 14th International Conference on Signal Processing and Communication Systems (ICSPCS), 2020
This paper includes the analysis and the results of the study of the possibility to utilize the unevenness coefficients of the use of individual graph edges for the assessment of the isomorphism of ICT networks described with Reference Graphs. These parameters are used to confirm or reject the presence of the isomorphism of the analyzed graphs.
Slawomir Bujnowski, Tomasz Marciniak, Olutayo Oyeyemi Oyerinde, Beata Marciniak, Zbigniew Lutowski   +4 more
openaire   +1 more source

Using Graph Isomorphism Network to Solve Graph Coloring Problem

2024 4th International Conference on Consumer Electronics and Computer Engineering (ICCECE)
Yicheng Zhang, Ni Wu
exaly   +2 more sources

On neural networks for graph isomorphism problem

[Proceedings] 1992 RNNS/IEEE Symposium on Neuroinformatics and Neurocomputers, 1992
Although the Hopfield neural networks is known to provide an efficient algorithm for hard problems, it cannot always give the correct solution due to local minima. For the graph isomorphism problem (which has not yet been proved to be polynomially solvable or NP-complete), the authors first introduce a Hopfield network that shows a similar behavior ...
K. Agusa, S. Fujita, M. Yamashita, T. Ae
openaire   +1 more source

Hypergraph Attention Isomorphism Network by Learning Line Graph Expansion

2020 IEEE International Conference on Big Data (Big Data), 2020
Graph neural networks (GNNs) are able to achieve state-of-the-art performance for node representation and classification in a network. But, most of the existing GNNs can be applied to simple graphs, where an edge connects only a pair of nodes. Studies have shown that hypergraphs are effective to model real-world relationships which are of higher order ...
Sambaran Bandyopadhyay, Kishalay Das, M. Narasimha Murty   +2 more
openaire   +1 more source

Influence of Krylov subspace in Graph Isomorphism for Mobile Networks

Mobile Networks and Applications, 2017
Identification of isomorphism among graphs is one of the computationally challenging tasks in computer science that couldn’t be solved in polynomial time. In this paper, we derive a polynomial time algorithm that allows direct comparison between different graph structures to check for graph isomorphism.
T. Ramraj, R. Prabhakar
openaire   +1 more source

Hyperspectral Image Classification via Neighborhood Adaptive Graph Isomorphism Network

IEEE Transactions on Geoscience and Remote Sensing
Bing Tu, Antonio Plaza, Bo Liu
exaly   +2 more sources

Graph isomorphisms effect on structure optimization of neural networks

Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290), 2003
Concepts from the graph theory and molecular evolution are proposed for analyzing effects of redundancy induced by graph isomorphisms on the structure optimization of neural networks. It is demonstrated that a graph database that considers isomorphisms can drastically reduce the number of evaluations in an evolutionary structure optimization process.
C. Igel, P. Stagge
openaire   +1 more source

Glyph graph isomorphism network for structure recognition of oracle bone inscription

Expert Systems With Applications
Zhan Zhang, Hanbin Liu, Yiyuan Wang
exaly   +2 more sources

Networks modulo graph isomorphism

2000
This chapter introduces the kernel of the network algebra, i.e., an algebraic theory of networks modulo graph isomorphism.
openaire   +1 more source

Graph Isomorphism Network for Speech Emotion Recognition

Interspeech 2021, 2021
Jiawang Liu, Haoxiang Wang 0002
openaire   +1 more source