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

Sequential recommendation is a fundamental task for network applications, andit usually suffers from the item cold start problem due to the insufficiency ofuser feedbacks. There are currently three kinds of popular approaches which arerespectively based on matrix factorization (MF) of collaborative filtering,Markov chain (MC), and recurrent neural network (RNN). Although widely used,they have some limitations. MF based methods could not capture dynamic user'sinterest. The strong Markov assumption greatly limits the performance of MCbased methods. RNN based methods are still in the early stage of incorporatingadditional information. Based on these basic models, many methods withadditional information only validate incorporating one modality in a separateway. In this work, to make the sequential recommendation and deal with the itemcold start problem, we propose a Multi-View Recurrent Neural Network (MV-RNN})model. Given the latent feature, MV-RNN can alleviate the item cold startproblem by incorporating visual and textual information. First, At the input ofMV-RNN, three different combinations of multi-view features are studied, likeconcatenation, fusion by addition and fusion by reconstructing the originalmulti-modal data. MV-RNN applies the recurrent structure to dynamically capturethe user's interest. Second, we design a separate structure and a unitedstructure on the hidden state of MV-RNN to explore a more effective way tohandle multi-view features. Experiments on two real-world datasets show thatMV-RNN can effectively generate the personalized ranking list, tackle themissing modalities problem and significantly alleviate the item cold startproblem.

MV-RNN: A Multi-View Recurrent Neural Network for Sequential Recommendation