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

Privacy has raised considerable concerns recently, especially with the adventof information explosion and numerous data mining techniques to explore theinformation inside large volumes of data. In this context, a new distributedlearning paradigm termed federated learning becomes prominent recently totackle the privacy issues in distributed learning, where only learning modelswill be transmitted from the distributed nodes to servers without revealingusers' own data and hence protecting the privacy of users.  In this paper, we propose a horizontal federated XGBoost algorithm to solvethe federated anomaly detection problem, where the anomaly detection aims toidentify abnormalities from extremely unbalanced datasets and can be consideredas a special classification problem. Our proposed federated XGBoost algorithmincorporates data aggregation and sparse federated update processes to balancethe tradeoff between privacy and learning performance. In particular, weintroduce the virtual data sample by aggregating a group of users' datatogether at a single distributed node. We compute parameters based on thesevirtual data samples in the local nodes and aggregate the learning model in thecentral server. In the learning model upgrading process, we focus more on thewrongly classified data before in the virtual sample and hence to generatesparse learning model parameters. By carefully controlling the size of thesegroups of samples, we can achieve a tradeoff between privacy and learningperformance. Our experimental results show the effectiveness of our proposedscheme by comparing with existing state-of-the-arts.

The Tradeoff Between Privacy and Accuracy in Anomaly Detection Using Federated XGBoost