We develop a new model, the Dual-Channel Network Embedding (DcNE), which integrates different types of network information into embeddings from a mutual ...

Network embedding is an important fundamental work in many network application tasks, which encodes the input network from the high-dimensional and sparse ...

Oct 1, 2023 · Specifically, we construct a dual-channel information propagation framework to encode the input network in semi-supervised and self-supervised ...

Oct 22, 2024 · Specifically, in attributed networks, normal nodes and their neighbors usually exhibit similar structural and attribute distribution states.

This research suggests a new way to find graph anomalies on attributed networks using random masking and padding along with sparse canonical correlation ...

Dual-channel embedding learning model for partially labeled attributed networks. https://doi.org/10.1016/j.patcog.2023.109644 ·. Journal: Pattern Recognition ...

Oct 22, 2024 · It can smoothly project different types of attributed information into the same semantic space through a deep attention model, while maintaining ...

Jul 19, 2023 · Dual-channel embedding learning model for partially labeled attributed networks. Pattern Recognition, Volume 142, 2023, Article 109644.

Dual-channel embedding learning model for partially labeled attributed networks · Author Picture Hangyuan Du, · Author Picture Wenjian Wang, · Author Picture Liang ...

This approach enables semi-supervised deep end-to-end clustering in attributed networks, promoting high structural cohesiveness and attribute homogeneity.