Results 1 to 10 of about 5,409,269 (206)
Learning to Solve NP-Complete Problems: A Graph Neural Network for Decision TSP [PDF]
AAAI Conference on Artificial Intelligence, 2019 Graph Neural Networks (GNN) are a promising technique for bridging differential programming and combinatorial domains. GNNs employ trainable modules which can be assembled in different configurations that reflect the relational structure of each problem ...
Marcelo Prates +9 more
openalex +3 more sources
SIGMA: Semantic-complete Graph Matching for Domain Adaptive Object Detection [PDF]
Computer Vision and Pattern Recognition, 2022 Domain Adaptive Object Detection (DAOD) leverages a labeled domain to learn an object detector generalizing to a novel domain free of annotations. Recent advances align class-conditional distributions by narrowing down cross-domain prototypes (class ...
Wuyang Li, Xinyu Liu, Yixuan Yuan
semanticscholar +1 more source
Some New Results on Lucky Labeling
مجلة بغداد للعلوم, 2023 Czerwi’nski et al. introduced Lucky labeling in 2009 and Akbari et al and A.Nellai Murugan et al studied it further. Czerwi’nski defined Lucky Number of graph as follows: A labeling of vertices of a graph G is called a Lucky labeling if for every pair ...
J. Ashwini +2 more
doaj +1 more source
Numerous graph energies of regular subdivision graph and complete graph
AIMS Mathematics, 2021 The graph energy E(G) of a simple graph G is sum of its absolute eigenvalues where eigenvalues of adjacency matrix A(G) are referred as eigenvalues of graph G. Depends upon eigenvalues of different graph matrices, several graph energies has been observed
Imrana Kousar +4 more
doaj +1 more source
Uniform (Ck, Pk+1)-Factorizations of Kn − I When k Is Even
Mathematics, 2022 Let H be a connected subgraph of a graph G. An H-factor of G is a spanning subgraph of G whose components are isomorphic to H. Given a set H of mutually non-isomorphic graphs, a uniform H-factorization of G is a partition of the edges of G into H-factors
Giovanni Lo Faro +2 more
doaj +1 more source
Shannon Entropy of Ramsey Graphs with up to Six Vertices
Entropy, 2023 Shannon entropy quantifying bi-colored Ramsey complete graphs is introduced and calculated for complete graphs containing up to six vertices. Complete graphs in which vertices are connected with two types of links, labeled as α-links and β-links, are ...
Mark Frenkel +2 more
doaj +1 more source
Spatio-temporal Graph Convolutional Neural Network: A Deep Learning Framework for Traffic Forecasting [PDF]
International Joint Conference on Artificial Intelligence, 2017 Timely accurate traffic forecast is crucial for urban traffic control and guidance. Due to the high nonlinearity and complexity of traffic flow, traditional methods cannot satisfy the requirements of mid-and-long term prediction tasks and often neglect ...
Ting Yu, Haoteng Yin, Zhanxing Zhu
semanticscholar +1 more source
Weak saturation numbers of and
AKCE International Journal of Graphs and Combinatorics, 2019 A graph is weakly -saturated if contains no copy of , and there is an ordering of all edges of so that if they are added one at a time, they form a complete graph and each edge added creates a new copy of .
Yajuan Cui, Liqun Pu
doaj +2 more sources
Self-avoiding walk on the complete graph [PDF]
Journal of the Mathematical Society of Japan, 2019 There is an extensive literature concerning self-avoiding walk on infinite graphs, but the subject is relatively undeveloped on finite graphs. The purpose of this paper is to elucidate the phase transition for self-avoiding walk on the simplest finite ...
G. Slade
semanticscholar +1 more source
The length of self-avoiding walks on the complete graph [PDF]
Journal of Statistical Mechanics: Theory and Experiment, 2019 We study the variable-length ensemble of self-avoiding walks on the complete graph. We obtain the leading order asymptotics of the mean and variance of the walk length, as the number of vertices goes to infinity.
Youjin Deng +4 more
semanticscholar +1 more source