Results 51 to 60 of about 228,260 (299)

Network representation learning based on social similarities

Frontiers in Environmental Science, 2022
Analysis of large-scale networks generally requires mapping high-dimensional network data to a low-dimensional space. We thus need to represent the node and connections accurate and effectively, and representation learning could be a promising method. In
Ziwei Mo, Zhenzhen Xie, Xilian Zhang, Qi Luo, Yanwei Zheng, Dongxiao Yu   +5 more
doaj   +1 more source

General support vector representation machine for one-class classification of non-stationary classes [PDF]

, 2008
Novelty detection, also referred to as one-class classification, is the process of detecting 'abnormal' behavior in a system by learning the 'normal' behavior.
Fatih Camci, Chinnam, R. B., Camci, Fatih, Ratna Babu Chinnam   +3 more
core   +1 more source

Road Network Representation Learning with Vehicle Trajectories

, 2023
Spatio-temporal traffic patterns reflecting the mobility behavior of road users are essential for learning effective general-purpose road representations.
Heinemeyer, Paul, Schestakov, Stefan, Demidova, Elena   +2 more
core   +1 more source

Network Representation Learning: From Traditional Feature Learning to Deep Learning

IEEE Access, 2020
Network representation learning (NRL) is an effective graph analytics technique and promotes users to deeply understand the hidden characteristics of graph data.
Ke Sun, Lei Wang, Bo Xu, Wenhong Zhao, Shyh Wei Teng, Feng Xia   +5 more
doaj   +1 more source

Attribute Network Representation Learning with Dual Autoencoders

, 2022
The purpose of attribute network representation learning is to learn the low-dimensional dense vector representation of nodes by combining structure and attribute information.
Jinghong Wang, Zhixia Zhou, Bi Li, Mancai Wu   +3 more
core   +1 more source

OFFER: A Motif Dimensional Framework for Network Representation Learning

, 2020
Aiming at better representing multivariate relationships, this paper investigates a motif dimensional framework for higher-order graph learning. The graph learning effectiveness can be improved through OFFER.
Lee, Ivan, Chen, Zhikui, Chen, Z., Xia, Feng, Shuo Yu, Jin Xu, Yu, S., Feng Xia, Xia, F., Lee, I., Xu, Jin, Xu, J., Zhikui Chen, Ivan Lee, Yu, Shuo   +14 more
core   +1 more source

Efficient Network Representation Learning via Cluster Similarity

Data Science and Engineering, 2023
Network representation learning is a de facto tool for graph analytics. The mainstream of the previous approaches is to factorize the proximity matrix between nodes.
Yasuhiro Fujiwara, Yasutoshi Ida, Atsutoshi Kumagai, Masahiro Nakano, Akisato Kimura, Naonori Ueda   +5 more
doaj   +1 more source

Identification of Key Nodes in Complex Networks Based on Network Representation Learning

IEEE Access, 2023
Recently, some research has utilized machine learning methods to identify critical nodes in complex networks. However, existing approaches often lack a comprehensive consideration of network structural features during node feature extraction.
Heping Zhang, Sicong Zhang, Xiaoyao Xie, Taihua Zhang, Guojun Yu   +4 more
doaj   +1 more source

Representation learning of dynamic networks

CoRR
This study presents a novel representation learning model tailored for dynamic networks, which describes the continuously evolving relationships among individuals within a population. The problem is encapsulated in the dimension reduction topic of functional data analysis.
Haixu Wang, Jiguo Cao, Jian Pei 0001
openaire   +2 more sources

Network Anomaly Detection Using Federated Learning and Transfer Learning

, 2020
Since deep neural networks can learn data representation from training data automatically, deep learning methods are widely used in the network anomaly detection.
Jian Teng, Guo, Qianling, Ying Zhao, Qianling Guo, Di Wu, Chen, Junjun, Teng, Jian, Wu, Di, Junjun Chen, Zhao, Ying   +9 more
core   +1 more source