English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Attributed network embedding has attracted plenty of interest in recentyears. It aims to learn task-independent, low-dimensional, and continuousvectors for nodes preserving both topology and attribute information. Most ofthe existing methods, such as random-walk based methods and GCNs, mainly focuson the local information, i.e., the attributes of the neighbours. Thus, theyhave been well studied for assortative networks (i.e., networks withcommunities) but ignored disassortative networks (i.e., networks withmultipartite, hubs, and hybrid structures), which are common in the real world.To enable model both assortative and disassortative networks, we propose ablock-based generative model for attributed network embedding from aprobability perspective. Specifically, the nodes are assigned to several blockswherein the nodes in the same block share the similar linkage patterns. Thesepatterns can define assortative networks containing communities ordisassortative networks with the multipartite, hub, or any hybrid structures.To preserve the attribute information, we assume that each node has a hiddenembedding related to its assigned block. We use a neural network tocharacterize the nonlinearity between node embeddings and node attributes. Weperform extensive experiments on real-world and synthetic attributed networks.The results show that our proposed method consistently outperformsstate-of-the-art embedding methods for both clustering and classificationtasks, especially on disassortative networks.

A Block-based Generative Model for Attributed Networks Embedding