Results 1 to 10 of about 6,608 (61)

wsGAT: Weighted and Signed Graph Attention Networks for Link Prediction [PDF]

, 2022
Graph Neural Networks (GNNs) have been widely used to learn representations on graphs and tackle many real-world problems from a wide range of domains. In this paper we propose wsGAT, an extension of the Graph Attention Network (GAT) layers, meant to address the lack of GNNs that can handle graphs with signed and weighted links, which are ubiquitous ...
Grassia M., Mangioni G.
openaire   +3 more sources

Nonlinear Merging Consensus for Multi-Agent Systems on Directed and Weighted Signed Graph [PDF]

IEEE Access, 2020
This paper settles the nonlinear merging consensus for multi-agent systems on a directed and weighted signed network. A novel nonlinear merging control protocol is proposed to drive the states of all agents to arrive at the same state. To be consistent with the reality, the interactions among agents can be either cooperative or competitive and the ...
Shasha Feng, Zijian Chen, Qunsheng Guan, Chengyi Xia   +3 more
openaire   +2 more sources

Weighted Modulo Orientations of Graphs and Signed Graphs

The Electronic Journal of Combinatorics, 2022
Given a graph $G$ and an odd prime $p$, for a mapping $f: E(G) \to {\mathbb Z}_p\setminus\{0\}$ and a ${\mathbb Z}_p$-boundary $b$ of $G$, an orientation $\tau$ is called an $(f,b;p)$-orientation if the net out $f$-flow is the same as $b(v)$ in ${\mathbb Z}_p$ at each vertex $v\in V(G)$ under orientation $D$.
Liu, Jianbing, Han, Miaomiao, Lai, Hong-Jian   +2 more
openaire   +1 more source

Polarization and multiscale structural balance in signed networks

Communications Physics, 2023
Polarization, or a division into mutually hostile groups, is a common feature of social systems. It is studied in Structural Balance Theory in terms of semicycles in signed networks.
Szymon Talaga, Massimo Stella, Trevor James Swanson, Andreia Sofia Teixeira   +3 more
doaj   +1 more source

Method Maximizing the Spread of Influence in Directed Signed Weighted Graphs

Advances in Electrical and Electronic Engineering, 2017
We propose a new method for maximizing the spread of influence, based on the identification of significant factors of the total energy of a control system.
Alexander Nikolaevich Tselykh, Vladislav Sergeevich Vasilev, Larisa Anatolievna Tselykh, Simon Antonovich Barkovskii   +3 more
doaj   +1 more source

Inertias of Laplacian matrices of weighted signed graphs

Special Matrices, 2019
We study the sets of inertias achieved by Laplacian matrices of weighted signed graphs. First we characterize signed graphs with a unique Laplacian inertia.
Monfared K. Hassani, MacGillivray G., Olesky D. D., van den Driessche P.   +3 more
doaj   +1 more source

Unveiling Early Signs of Preclinical Alzheimer’s Disease Through ERP Analysis with Weighted Visibility Graphs and Ensemble Learning

Bioengineering
The early detection of Alzheimer’s disease (AD) is important for effective therapeutic interventions and optimized enrollment for clinical trials. Recent studies have shown high accuracy in identifying mild AD by applying visibility graph and machine learning methods to electroencephalographic (EEG) data.
Yongshuai Liu, Jiangyi Xia, Ziwen Kan, Jesse Zhang, Sheela Toprani, James B. Brewer, Marta Kutas, Xin Liu, John Olichney   +8 more
openaire   +2 more sources

REPEL - Random Embedding Perturbation for Enhanced Learning of Protein Function. [PDF]

Pac Symp Biocomput
Zhou D, Cowen LJ, Wu K, Hu X, Slonim DK.
europepmc   +1 more source

Graph neural network-based mutation-aware regression test ordering using code dependency graphs and execution traces. [PDF]

MethodsX
Sowmyadevi S, Alphy A.
europepmc   +1 more source

Spike-based time-domain analog weighted-sum calculation model for extremely low power VLSI implementation of multi-layer neural networks. [PDF]

Front Neurosci
Wang Q, Tamukoh H, Morie T.
europepmc   +1 more source