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/

Zendy Plus

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

Zendy Tools

Zendy Open

Higher-order proximity preserved network embedding has attracted increasingattention. In particular, due to the superior scalability, random-walk-basednetwork embedding has also been well developed, which could efficiently explorehigher-order neighborhoods via multi-hop random walks. However, despite thesuccess of current random-walk-based methods, most of them are usually notexpressive enough to preserve the personalized higher-order proximity and lacka straightforward objective to theoretically articulate what and how networkproximity is preserved. In this paper, to address the above issues, we presenta general scalable random-walk-based network embedding framework, in whichrandom walk is explicitly incorporated into a sound objective designedtheoretically to preserve arbitrary higher-order proximity. Further, weintroduce the random walk with restart process into the framework to naturallyand effectively achieve personalized-weighted preservation of proximities ofdifferent orders. We conduct extensive experiments on several real-worldnetworks and demonstrate that our proposed method consistently andsubstantially outperforms the state-of-the-art network embedding methods.

RWNE: A Scalable Random-Walk-Based Network Embedding Framework with Personalized Higher-Order Proximity Preserved