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

Consensus-based decentralized stochastic gradient descent (D-SGD) is a widelyadopted algorithm for decentralized training of machine learning models acrossnetworked agents. A crucial part of D-SGD is the consensus-based modelaveraging, which heavily relies on information exchange and fusion among thenodes. Specifically, for consensus averaging over wireless networks,communication coordination is necessary to determine when and how a node canaccess the channel and transmit (or receive) information to (or from) itsneighbors. In this work, we propose $\texttt{BASS}$, a broadcast-based subgraphsampling method designed to accelerate the convergence of D-SGD whileconsidering the actual communication cost per iteration. $\texttt{BASS}$creates a set of mixing matrix candidates that represent sparser subgraphs ofthe base topology. In each consensus iteration, one mixing matrix is sampled,leading to a specific scheduling decision that activates multiplecollision-free subsets of nodes. The sampling occurs in a probabilistic manner,and the elements of the mixing matrices, along with their samplingprobabilities, are jointly optimized. Simulation results demonstrate that$\texttt{BASS}$ enables faster convergence with fewer transmission slotscompared to existing link-based scheduling methods. In conclusion, the inherentbroadcasting nature of wireless channels offers intrinsic advantages inaccelerating the convergence of decentralized optimization and learning.

Faster Convergence with Less Communication: Broadcast-Based Subgraph Sampling for Decentralized Learning over Wireless Networks