AI Paper Atlas

Research map / Federated learning and privacy / Communication-efficient FL

FedCBO: Reaching Group Consensus in Clustered Federated Learning through Consensus-based Optimization

José A. Carrillo, Nicolás García Trillos, Sixu Li, Yuhua Zhu

JMLR 2024 · Federated learning and privacy › Communication-efficient FL · approach: Federated optimization algorithms · 13 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use FedCBO consensus-based aggregation instead of IFCAFedCBO · Rotated MNIST (N=1200 agents, 4 rotation clusters)test accuracy (%): 94.44 -> 96.51Improved
use FedCBO instead of single-model FedAvgFedCBO · Rotated MNIST (N=1200 agents, 4 rotation clusters)test accuracy (%): 85.50 -> 96.51Improved
add communication via FedCBO instead of local training onlyFedCBO · Rotated MNIST (N=1200 agents, 4 rotation clusters)test accuracy (%): 81.27 -> 96.51Improved
use IFCA cluster models instead of one FedAvg modelIFCA · Rotated MNIST (N=1200 agents, 4 rotation clusters)test accuracy (%): 85.50 -> 94.44Improved
collaborate via FedAvg instead of local trainingFedAvg · Rotated MNIST (N=1200 agents, 4 rotation clusters)test accuracy (%): 81.27 -> 85.50Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy