Results 1 to 10 of about 845,204 (303)
Survey on Applications of Knowledge Graph Embedding in Recommendation Tasks [PDF]
Jisuanji kexue yu tansuo, 2022 Recommendation systems are designed to recommend personalized content to improve user experience. At present, the recommendation systems still face some challenges such as poor interpretability, cold start problem and serialized recommendation modeling ...
TIAN Xuan, CHEN Hangxue
doaj +1 more source
Advances in Knowledge Graph Embedding Based on Graph Neural Networks [PDF]
Jisuanji kexue yu tansuo, 2023 As graph neural networks continue to develop, knowledge graph embedding methods based on graph neural networks are receiving increasing attention from researchers.
YAN Zhaoyao, DING Cangfeng, MA Lerong, CAO Lu, YOU Hao
doaj +1 more source
Graph Embedding Models: A Survey [PDF]
Jisuanji kexue yu tansuo, 2022 Effective graph analysis methods can reveal the intrinsic characteristics of graph data. However, graph is non-Euclidean data, which leads to high computation and space cost while applying traditional methods.
YUAN Lining, LI Xin, WANG Xiaodong, LIU Zhao
doaj +1 more source
Graph Embedding via Graph Summarization
IEEE Access, 2021 Graph representation learning aims to represent the structural and semantic information of graph objects as dense real value vectors in low dimensional space by machine learning.
Jingyanning Yang +2 more
doaj +1 more source
Proximity-Based Compression for Network Embedding
Frontiers in Big Data, 2021 Network embedding that encodes structural information of graphs into a low-dimensional vector space has been proven to be essential for network analysis applications, including node classification and community detection.
Muhammad Ifte Islam +4 more
doaj +1 more source
Fast Unsupervised Graph Embedding Based on Anchors [PDF]
Jisuanji kexue, 2022 Graph embedding is a widely used method for dimensionality reduction due to its computational effectiveness.The computational complexity of graph embedding method to construct traditional K-Nearest Neighbors (K-NN) graph is at least O(n2d), where n and d
YANG Hui, TAO Li-hong, ZHU Jian-yong, NIE Fei-ping
doaj +1 more source
Graph Embedding Framework Based on Adversarial and Random Walk Regularization
IEEE Access, 2021 Graph embedding aims to represent node structural as well as attribute information into a low-dimensional vector space so that some downstream application tasks such as node classification, link prediction, community detection, and recommendation can be ...
Wei Dou +3 more
doaj +1 more source
Plausible Heterogeneous Graph k-Anonymization for Social Networks
Tsinghua Science and Technology, 2022 The inefficient utilization of ubiquitous graph data with combinatorial structures necessitates graph embedding methods, aiming at learning a continuous vector space for the graph which is amenable to be adopted in traditional machine learning algorithms
Kaiyang Li, Ling Tian, Xu Zheng, Bei Hui
doaj +1 more source
Embedding into Bipartite Graphs [PDF]
SIAM Journal on Discrete Mathematics, 2010 The conjecture of Bollobás and Komlós, recently proved by Böttcher, Schacht, and Taraz [Math. Ann. 343(1), 175--205, 2009], implies that for any $γ>0$, every balanced bipartite graph on $2n$ vertices with bounded degree and sublinear bandwidth appears as a subgraph of any $2n$-vertex graph $G$ with minimum degree $(1+γ)n$, provided that $n$ is ...
Julia Böttcher +2 more
openaire +3 more sources
Link-Privacy Preserving Graph Embedding Data Publication with Adversarial Learning
Tsinghua Science and Technology, 2022 The inefficient utilization of ubiquitous graph data with combinatorial structures necessitates graph embedding methods, aiming at learning a continuous vector space for the graph, which is amenable to be adopted in traditional machine learning ...
Kainan Zhang +3 more
doaj +1 more source