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

In the current deep learning based recommendation system, the embeddingmethod is generally employed to complete the conversion from thehigh-dimensional sparse feature vector to the low-dimensional dense featurevector. However, as the dimension of the input vector of the embedding layer istoo large, the addition of the embedding layer significantly slows down theconvergence speed of the entire neural network, which is not acceptable inreal-world scenarios. In addition, as the interaction between users and itemsincreases and the relationship between items becomes more complicated, theembedding method proposed for sequence data is no longer suitable for graphicdata in the current real environment. Therefore, in this paper, we propose theDual-modal Graph Embedding Method (DGEM) to solve these problems. DGEM includestwo modes, static and dynamic. We first construct the item graph to extract thegraph structure and use random walk of unequal probability to capture thehigh-order proximity between the items. Then we generate the graph embeddingvector through the Skip-Gram model, and finally feed the downstream deep neuralnetwork for the recommendation task. The experimental results show that DGEMcan mine the high-order proximity between items and enhance the expressionability of the recommendation model. Meanwhile it also improves therecommendation performance by utilizing the time dependent relationship betweenitems.

DGEM: A New Dual-modal Graph Embedding Method in Recommendation System