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

User attribute prediction is a crucial task in various industries. However,sharing user data across different organizations faces challenges due toprivacy concerns and legal requirements regarding personally identifiableinformation. Regulations such as the General Data Protection Regulation (GDPR)in the European Union and the Personal Information Protection Law of thePeople's Republic of China impose restrictions on data sharing. To address theneed for utilizing features from multiple clients while adhering to legalrequirements, federated learning algorithms have been proposed. Thesealgorithms aim to predict user attributes without directly sharing the data.However, existing approaches typically rely on matching users across companies,which can result in dishonest partners discovering user lists or the inabilityto utilize all available features. In this paper, we propose a novel algorithmfor predicting user attributes without requiring user matching. Our approachinvolves training deep matrix factorization models on different clients andsharing only the item vectors. This allows us to predict user attributeswithout sharing the user vectors themselves. The algorithm is evaluated usingthe publicly available MovieLens dataset and demonstrate that it achievessimilar performance to the FedAvg algorithm, reaching 96% of a single model'saccuracy. The proposed algorithm is particularly well-suited for improvingcustomer targeting and enhancing the overall customer experience. This paperpresents a valuable contribution to the field of user attribute prediction byoffering a novel algorithm that addresses some of the most pressing privacyconcerns in this area.

FedDMF: Privacy-Preserving User Attribute Prediction using Deep Matrix Factorization