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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

The prevalence of online social network makes it compulsory to study howsocial relations affect user choice. However, most existing methods leverageonly first-order social relations, that is, the direct neighbors that areconnected to the target user. The high-order social relations, e.g., thefriends of friends, which very informative to reveal user preference, have beenlargely ignored. In this work, we focus on modeling the indirect influence fromthe high-order neighbors in social networks to improve the performance of itemrecommendation. Distinct from mainstream social recommenders that regularizethe model learning with social relations, we instead propose to directly factorsocial relations in the predictive model, aiming at learning better userembeddings to improve recommendation. To address the challenge that high-orderneighbors increase dramatically with the order size, we propose to recursively"propagate" embeddings along the social network, effectively injecting theinfluence of high-order neighbors into user representation. We conductexperiments on two real datasets of Yelp and Douban to verify our High-OrderSocial Recommender (HOSR) model. Empirical results show that our HOSRsignificantly outperforms recent graph regularization-based recommenders NSCRand IF-BPR+, and graph convolutional network-based social influence predictionmodel DeepInf, achieving new state-of-the-arts of the task.

Modelling High-Order Social Relations for Item Recommendation