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

Non-negative matrix factorization (NMF) with missing-value completion is awell-known effective Collaborative Filtering (CF) method used to providepersonalized user recommendations. However, traditional CF relies on theprivacy-invasive collection of users' explicit and implicit feedback to build acentral recommender model. One-shot federated learning has recently emerged asa method to mitigate the privacy problem while addressing the traditionalcommunication bottleneck of federated learning. In this paper, we present thefirst unsupervised one-shot federated CF implementation, named FedSPLIT, basedon NMF joint factorization. In our solution, the clients first apply local CFin-parallel to build distinct client-specific recommenders. Then, theprivacy-preserving local item patterns and biases from each client are sharedwith the processor to perform joint factorization in order to extract theglobal item patterns. Extracted patterns are then aggregated to each client tobuild the local models via knowledge distillation. In our experiments, wedemonstrate the feasibility of our approach with standard recommendationdatasets. FedSPLIT can obtain similar results than the state of the art (andeven outperform it in certain situations) with a substantial decrease in thenumber of communications.

FedSPLIT: One-Shot Federated Recommendation System Based on Non-negative Joint Matrix Factorization and Knowledge Distillation