Network representation learning: A survey
With the widespread use of information technologies, information networks are becoming
increasingly popular to capture complex relationships across various disciplines, such as …
increasingly popular to capture complex relationships across various disciplines, such as …
Deep anomaly detection on attributed networks
Attributed networks are ubiquitous and form a critical component of modern information
infrastructure, where additional node attributes complement the raw network structure in …
infrastructure, where additional node attributes complement the raw network structure in …
Co-embedding attributed networks
Existing embedding methods for attributed networks aim at learning low-dimensional vector
representations for nodes only but not for both nodes and attributes, resulting in the fact that …
representations for nodes only but not for both nodes and attributes, resulting in the fact that …
Interactive anomaly detection on attributed networks
Performing anomaly detection on attributed networks concerns with finding nodes whose
patterns or behaviors deviate significantly from the majority of reference nodes. Its success …
patterns or behaviors deviate significantly from the majority of reference nodes. Its success …
Shne: Representation learning for semantic-associated heterogeneous networks
Representation learning in heterogeneous networks faces challenges due to
heterogeneous structural information of multiple types of nodes and relations, and also due …
heterogeneous structural information of multiple types of nodes and relations, and also due …
Graph recurrent networks with attributed random walks
Random walks are widely adopted in various network analysis tasks ranging from network
embedding to label propagation. It could capture and convert geometric structures into …
embedding to label propagation. It could capture and convert geometric structures into …
Is a single vector enough? exploring node polysemy for network embedding
Networks have been widely used as the data structure for abstracting real-world systems as
well as organizing the relations among entities. Network embedding models are powerful …
well as organizing the relations among entities. Network embedding models are powerful …
AnomMAN: Detect anomalies on multi-view attributed networks
Anomaly detection on attributed networks is widely used in online shopping, financial
transactions, communication networks, and so on. However, most existing works trying to …
transactions, communication networks, and so on. However, most existing works trying to …
Robust negative sampling for network embedding
Many recent network embedding algorithms use negative sampling (NS) to approximate a
variant of the computationally expensive Skip-Gram neural network architecture (SGA) …
variant of the computationally expensive Skip-Gram neural network architecture (SGA) …
Semi-supervisedly co-embedding attributed networks
Deep generative models (DGMs) have achieved remarkable advances. Semi-supervised
variational auto-encoders (SVAE) as a classical DGM offers a principled framework to …
variational auto-encoders (SVAE) as a classical DGM offers a principled framework to …