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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Given multiple input signals, how can we infer node importance in a knowledgegraph (KG)? Node importance estimation is a crucial and challenging task thatcan benefit a lot of applications including recommendation, search, and querydisambiguation. A key challenge towards this goal is how to effectively useinput from different sources. On the one hand, a KG is a rich source ofinformation, with multiple types of nodes and edges. On the other hand, thereare external input signals, such as the number of votes or pageviews, which candirectly tell us about the importance of entities in a KG. While severalmethods have been developed to tackle this problem, their use of these externalsignals has been limited as they are not designed to consider multiple signalssimultaneously. In this paper, we develop an end-to-end model MultiImport,which infers latent node importance from multiple, potentially overlapping,input signals. MultiImport is a latent variable model that captures therelation between node importance and input signals, and effectively learns frommultiple signals with potential conflicts. Also, MultiImport provides aneffective estimator based on attentive graph neural networks. We ranexperiments on real-world KGs to show that MultiImport handles severalchallenges involved with inferring node importance from multiple input signals,and consistently outperforms existing methods, achieving up to 23.7% higherNDCG@100 than the state-of-the-art method.

MultiImport: Inferring Node Importance in a Knowledge Graph from Multiple Input Signals