AI Paper Atlas

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

Personalized Federated Learning with Bidirectional Communication Compression via One-Bit Random Sketching

Jiacheng Cheng, Xu Zhang, Guanghui Qiu, Yifang Zhang, Yinchuan Li, Kaiyuan Feng

AAAI 2026 · Federated learning and privacy › Communication-efficient FL · approach: Communication-efficient heterogeneous FL · 1 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 pFed1BS instead of full-precision FedAvgFL baseline · CIFAR-100top-1 accuracy (%): 59.60 -> 52.88Hurt
use pFed1BS instead of full-precision FedAvgFL baseline · CIFAR-10top-1 accuracy (%): 87.78 -> 85.21Hurt
use pFed1BS instead of full-precision FedAvgFL baseline · SVHNtop-1 accuracy (%): 96.33 -> 95.07Hurt
use pFed1BS instead of full-precision FedAvgFL baseline · FMNISTtop-1 accuracy (%): 84.40 -> 84.15No clear effect
use pFed1BS instead of full-precision FedAvgFL baseline · MNISTtop-1 accuracy (%): 97.21 -> 97.83Improved
use pFed1BS instead of OBDA one-bit baselineOBDA · CIFAR-100top-1 accuracy (%): 42.47 -> 52.88Improved
use pFed1BS instead of OBDA one-bit baselineOBDA · CIFAR-10top-1 accuracy (%): 73.26 -> 85.21Improved
use pFed1BS instead of EDENEDEN · SVHNtop-1 accuracy (%): 89.01 -> 95.07Improved
use pFed1BS instead of FedBATFedBAT · CIFAR-100top-1 accuracy (%): 46.89 -> 52.88Improved
use pFed1BS instead of FedAvg for communicationFedAvg · CIFAR-10per-round communication cost (MB): 42.85 -> 0.13Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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