A survey on heterogeneous graph embedding: methods, techniques, applications and sources
Heterogeneous graphs (HGs) also known as heterogeneous information networks have
become ubiquitous in real-world scenarios; therefore, HG embedding, which aims to learn …
become ubiquitous in real-world scenarios; therefore, HG embedding, which aims to learn …
Graph neural networks: foundation, frontiers and applications
The field of graph neural networks (GNNs) has seen rapid and incredible strides over the
recent years. Graph neural networks, also known as deep learning on graphs, graph …
recent years. Graph neural networks, also known as deep learning on graphs, graph …
[HTML][HTML] A survey on heterogeneous information network based recommender systems: Concepts, methods, applications and resources
As an important way to alleviate information overload, a recommender system aims to filter
out irrelevant information for users and provides them items that they may be interested in. In …
out irrelevant information for users and provides them items that they may be interested in. In …
Motif-backdoor: Rethinking the backdoor attack on graph neural networks via motifs
H Zheng, H **ong, J Chen, H Ma… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Graph neural network (GNN) with a powerful representation capability has been widely
applied to various areas. Recent works have exposed that GNN is vulnerable to the …
applied to various areas. Recent works have exposed that GNN is vulnerable to the …
Network embedding via motifs
Network embedding has emerged as an effective way to deal with downstream tasks, such
as node classification [,,]. Most existing methods leverage multi-similarities between nodes …
as node classification [,,]. Most existing methods leverage multi-similarities between nodes …
SHNE: Semantics and homophily preserving network embedding
Z Zhang, C Chen, Y Chang, W Hu… - … on Neural Networks …, 2021 - ieeexplore.ieee.org
Graph convolutional networks (GCNs) have achieved great success in many applications
and have caught significant attention in both academic and industrial domains. However …
and have caught significant attention in both academic and industrial domains. However …
Hypergraph motifs and their extensions beyond binary
Hypergraphs naturally represent group interactions, which are omnipresent in many
domains: collaborations of researchers, co-purchases of items, and joint interactions of …
domains: collaborations of researchers, co-purchases of items, and joint interactions of …
Short text topic learning using heterogeneous information network
With the explosive growth of short texts on users' interests and preferences, learning
discriminative and coherent latent topics from short texts is a critical and significative work …
discriminative and coherent latent topics from short texts is a critical and significative work …
[BOOK][B] Heterogeneous graph representation learning and applications
Heterogeneous graph, containing different types of nodes and links, is ubiquitous in the real
world, ranging from bibliographic networks and social networks to recommendation systems …
world, ranging from bibliographic networks and social networks to recommendation systems …
Motif graph neural network
Graphs can model complicated interactions between entities, which naturally emerge in
many important applications. These applications can often be cast into standard graph …
many important applications. These applications can often be cast into standard graph …