Results 11 to 20 of about 2,708,601 (295)
Learning Weight Signed Network Embedding with Graph Neural Networks
Data Science and Engineering, 2023 Network embedding aims to map nodes in a network to low-dimensional vector representations. Graph neural networks (GNNs) have received much attention and have achieved state-of-the-art performance in learning node representation.
Zekun Lu +4 more
doaj +2 more sources
Signed graph representation learning for functional-to-structural brain network mapping [PDF]
Med Image Anal, 2022 Haoteng Tang +9 more
semanticscholar +2 more sources
Eigenspaces for \(-2\) in signed line graphs
The American Journal of CombinatoricsIt is known that \(-2\) appears in the spectrum of a connected signed line graph if and only if its root is either (a) a balanced signed graph, not a tree, that spans a switching of the complete signed graph or (b) an unbalanced simply signed graph ...
Zoran Stanić
doaj +3 more sources
On Singular Signed Graphs with Nullspace Spanned by a Full Vector: Signed Nut Graphs
Discussiones Mathematicae Graph Theory, 2022 A signed graph has edge weights drawn from the set {+1, −1}, and is sign-balanced if it is equivalent to an unsigned graph under the operation of sign switching; otherwise it is sign-unbalanced.
Bašić Nino +3 more
doaj +2 more sources
Black-Box Attacks Against Signed Graph Analysis via Balance Poisoning [PDF]
International Conference on Computing, Networking and Communications, 2023 Signed graphs are well-suited for modeling social networks as they capture both positive and negative relationships. Signed graph neural networks (SGNNs) are commonly employed to predict link signs (i.e., positive and negative) in such graphs due to ...
Jialong Zhou, Y. Lai, Jian Ren, Kai Zhou
semanticscholar +1 more source
Signed Graph Neural Networks: A Frequency Perspective [PDF]
Trans. Mach. Learn. Res., 2022 Graph convolutional networks (GCNs) and its variants are designed for unsigned graphs containing only positive links. Many existing GCNs have been derived from the spectral domain analysis of signals lying over (unsigned) graphs and in each convolution ...
Rahul Singh, Yongxin Chen
semanticscholar +1 more source
Negative (and positive) circles in signed graphs: A problem collection
AKCE International Journal of Graphs and Combinatorics, 2018 A signed graph is a graph whose edges are labeled positive or negative. The sign of a circle (cycle, circuit) is the product of the signs of its edges. Most of the essential properties of a signed graph depend on the signs of its circles. Here I describe
Thomas Zaslavsky
doaj +2 more sources
Advances in Scaling Community Discovery Methods for Large Signed Graph Networks [PDF]
J. Complex Networks, 2021 Community detection is a common task in social network analysis (SNA) with applications in a variety of fields including medicine, criminology, and business. Despite the popularity of community detection, there is no clear consensus on the most effective
Maria E. Tomasso +2 more
semanticscholar +1 more source
Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, 2022 With both positive and negative links, signed graphs exist widely in the real world. Recently, signed graph neural networks (GNNs) have shown superior performance in the most common signed graph analysis task, i.e., link sign prediction.
Haoxin Liu
semanticscholar +1 more source
Laplacian integral signed graphs with few cycles
AIMS Mathematics, 2023 A connected graph with n vertices and m edges is called k-cyclic graph if k=m−n+1. We call a signed graph is Laplacian integral if all eigenvalues of its Laplacian matrix are integers.
Dijian Wang, Dongdong Gao
doaj +1 more source