Results 51 to 60 of about 170,883 (277)
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 +1 more source
An Algebra of Hierarchical Graphs [PDF]
, 2010 We define an algebraic theory of hierarchical graphs, whose axioms characterise graph isomorphism: two terms are equated exactly when they represent the same graph.
A. Boronat +16 more
core +4 more sources
Temporal and Spatial Information Enhanced Heterogeneous Information Network Embedding
IEEE AccessHeterogeneous Information Network (HIN) embedding learns low-dimensional representations of nodes while preserving temporal and spatial information. Although some HIN embedding methods have been proposed, they did not fully use the temporal and spatial ...
Susu Zheng, Weiwei Yuan
doaj +1 more source
ACE: Ant Colony Based Multi-Level Network Embedding for Hierarchical Graph Representation Learning
IEEE Access, 2019 As a popularly used technique for feature learning in graphs, network embedding aims to represent each node as a low-dimensional vector to support efficient graph analytic tasks, such as node classification, link prediction, and visualization. The key to
Jianming Lv +3 more
doaj +1 more source
Relation Structure-Aware Heterogeneous Information Network Embedding
, 2019 Heterogeneous information network (HIN) embedding aims to embed multiple types of nodes into a low-dimensional space. Although most existing HIN embedding methods consider heterogeneous relations in HINs, they usually employ one single model for all ...
Hu, Linmei +3 more
core +1 more source
Structural Node Embeddings with Homomorphism Counts
CoRR, 2023 Graph homomorphism counts, first explored by Lovász in 1967, have recently garnered interest as a powerful tool in graph-based machine learning. Grohe (PODS 2020) proposed the theoretical foundations for using homomorphism counts in machine learning on graph level as well as node level tasks.
Wolf, Hinrikus +3 more
openaire +3 more sources
Molecular Oncology, EarlyView.Single circulating tumor cells (sCTCs) from high‐grade serous ovarian cancer patients were enriched, imaged, and genomically profiled using WGA and NGS at different time points during treatment. sCTCs revealed enrichment of alterations in Chromosomes 2, 7, and 12 as well as persistent or emerging oncogenic CNAs, supporting sCTC identity.
Carolin Salmon +9 more
wiley +1 more source
Virtual network embedding method based on node delay perception
IET NetworksWireless virtual network uses software defined network and network function virtualisation technologies to create multiple logically isolated virtual networks on a physical wireless network.
Yaning Wang, Hui Zhi
doaj +1 more source
NodeVector: A Novel Network Node Vectorization with Graph Analysis and Deep Learning
Applied SciencesNetwork node embedding captures structural and relational information of nodes in the network and allows for us to use machine learning algorithms for various prediction tasks on network data that have an inherently complex and disordered structure ...
Volkan Altuntas
doaj +1 more source
Semi-AttentionAE: An Integrated Model for Graph Representation Learning
IEEE Access, 2021 Graph embedding learns low-dimensional vector representations which capture and preserve information in original graphs. Common shallow neural networks and deep autoencoder only use adjacency matrix as input, and usually ignore node attributes and ...
Lining Yuan +3 more
doaj +1 more source