Results 61 to 70 of about 8,152,507 (265)
The Surprising Power of Graph Neural Networks with Random Node Initialization [PDF]
International Joint Conference on Artificial Intelligence, 2020 Graph neural networks (GNNs) are effective models for representation learning on relational data. However, standard GNNs are limited in their expressive power, as they cannot distinguish graphs beyond the capability of the Weisfeiler-Leman graph ...
Ralph Abboud +3 more
semanticscholar +1 more source
Power Flow Balancing With Decentralized Graph Neural Networks [PDF]
IEEE Transactions on Power Systems, 2021 We propose an end-to-end framework based on a Graph Neural Network (GNN) to balance the power flows in energy grids. The balancing is framed as a supervised vertex regression task, where the GNN is trained to predict the current and power injections at ...
Jonas Berg Hansen +2 more
semanticscholar +1 more source
Note On The Game Colouring Number Of Powers Of Graphs
Discussiones Mathematicae Graph Theory, 2016 We generalize the methods of Esperet and Zhu [6] providing an upper bound for the game colouring number of squares of graphs to obtain upper bounds for the game colouring number of m-th powers of graphs, m ≥ 3, which rely on the maximum degree and the ...
Andres Stephan Dominique, Theuser Andrea
doaj +1 more source
Real Quadratic-Form-Based Graph Pooling for Graph Neural Networks
Machine Learning and Knowledge Extraction, 2022 Graph neural networks (GNNs) have developed rapidly in recent years because they can work over non-Euclidean data and possess promising prediction power in many real-word applications.
Youfa Liu, Guo Chen
doaj +1 more source
THE POWER GRAPH REPRESENTATION FOR INTEGER MODULO GROUP WITH POWER PRIME ORDER
BAREKENG JURNAL ILMU MATEMATIKA DAN TERAPAN, 2023 There are many applications of graphs in various fields. Starting from chemical problems, such as the molecular shape of a compound to internet network problems, we can also use graphs to depict the abstract concept of a mathematical structure..
Lalu Riski +6 more
semanticscholar +1 more source
SHACL-Based Validation Method of Knowledge Graph for Power System Model
Zhongguo dianli, 2022 With the expansion of the power grid and the high penetration of distributed energy resources, the power system analysis and decision-making have put forward higher requirements for comprehensive and accurate power grid models.
Xiaolu LI +5 more
doaj +1 more source
Average Degree in Graph Powers [PDF]
Journal of Graph Theory, 2012 AbstractThe kth power of a simple graph G, denoted by , is the graph with vertex set where two vertices are adjacent if they are within distance k in G. We are interested in finding lower bounds on the average degree of . Here we prove that if G is connected with minimum degree and , then G4 has average degree at least .
DeVos, Matt +2 more
openaire +3 more sources
Power domination in Kn\"odel graphs and Hanoi graphs
Discussiones Mathematicae Graph Theory, 2018 zbMATH Open Web Interface contents unavailable due to conflicting licenses.
Varghese, Seethu +2 more
openaire +3 more sources
Some Graph Polynomials of the Power Graph and its Supergraphs [PDF]
Mathematics Interdisciplinary Research, 2020 In this paper, exact formulas for the dependence, independence, vertex cover and clique polynomials of the power graph and its supergraphs for certain finite groups are presented.
Asma Hamzeh
doaj +1 more source
Accessibility percolation on Cartesian power graphs
Journal of Mathematical Biology, 2023 AbstractA fitness landscape is a mapping from a space of discrete genotypes to the real numbers. A path in a fitness landscape is a sequence of genotypes connected by single mutational steps. Such a path is said to be accessible if the fitness values of the genotypes encountered along the path increase monotonically. We study accessible paths on random
Benjamin Schmiegelt, Joachim Krug
openaire +4 more sources