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

We study the problem of large-scale network embedding, which aims to learnlow-dimensional latent representations for network mining applications. Recentresearch in the field of network embedding has led to significant progress suchas DeepWalk, LINE, NetMF, NetSMF. However, the huge size of many real-worldnetworks makes it computationally expensive to learn network embedding from theentire network. In this work, we present a novel network embedding methodcalled "NES", which learns network embedding from a small representativesubgraph. NES leverages theories from graph sampling to efficiently constructrepresentative subgraph with smaller size which can be used to make inferencesabout the full network, enabling significantly improved efficiency in embeddinglearning. Then, NES computes the network embedding from this representativesubgraph, efficiently. Compared with well-known methods, extensive experimentson networks of various scales and types demonstrate that NES achievescomparable performance and significant efficiency superiority.

Learning Large-scale Network Embedding from Representative Subgraph