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

Distributed machine learning (DML) over time-varying networks can be anenabler for emerging decentralized ML applications such as autonomous drivingand drone fleeting. However, the commonly used weighted arithmetic mean modelaggregation function in existing DML systems can result in high model loss, lowmodel accuracy, and slow convergence speed over time-varying networks. Toaddress this issue, in this paper, we propose a novel non-linear class of modelaggregation functions to achieve efficient DML over time-varying networks.Instead of taking a linear aggregation of neighboring models as most existingstudies do, our mechanism uses a nonlinear aggregation, a weighted power-p mean(WPM), as the aggregation function of local models from neighbors. Thesubsequent optimizing steps are taken using mirror descent defined by a Bregmandivergence that maintains convergence to optimality. In this paper, we analyzeproperties of the WPM and rigorously prove convergence properties of ouraggregation mechanism. Additionally, through extensive experiments, we showthat when p > 1, our design significantly improves the convergence speed of themodel and the scalability of DML under time-varying networks compared witharithmetic mean aggregation functions, with little additional computationoverhead.

Achieving Efficient Distributed Machine Learning Using a Novel Non-Linear Class of Aggregation Functions